Stop the war!Остановите войну!
for scientists:
default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDBibTeX records: Hynek Hermansky
@inproceedings{DBLP:conf/icassp/SadhuH23,
author = {Samik Sadhu and
Hynek Hermansky},
title = {Importance of Different Temporal Modulations of Speech: a Tale of
two Perspectives},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing
{ICASSP} 2023, Rhodes Island, Greece, June 4-10, 2023},
pages = {1--5},
publisher = {{IEEE}},
year = {2023},
url = {https://doi.org/10.1109/ICASSP49357.2023.10095972},
doi = {10.1109/ICASSP49357.2023.10095972},
timestamp = {Sun, 05 Nov 2023 16:51:21 +0100},
biburl = {https://dblp.org/rec/conf/icassp/SadhuH23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2303-04187,
author = {Martin Sustek and
Samik Sadhu and
Luk{\'{a}}s Burget and
Hynek Hermansky and
Jes{\'{u}}s Villalba and
Laureano Moro{-}Vel{\'{a}}zquez and
Najim Dehak},
title = {Stabilized training of joint energy-based models and their practical
applications},
journal = {CoRR},
volume = {abs/2303.04187},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2303.04187},
doi = {10.48550/ARXIV.2303.04187},
eprinttype = {arXiv},
eprint = {2303.04187},
timestamp = {Thu, 16 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2303-04187.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2303-12908,
author = {Samik Sadhu and
Hynek Hermansky},
title = {Self-supervised Learning with Speech Modulation Dropout},
journal = {CoRR},
volume = {abs/2303.12908},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2303.12908},
doi = {10.48550/ARXIV.2303.12908},
eprinttype = {arXiv},
eprint = {2303.12908},
timestamp = {Thu, 13 Apr 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2303-12908.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/SustekSH22,
author = {Martin Sustek and
Samik Sadhu and
Hynek Hermansky},
editor = {Hanseok Ko and
John H. L. Hansen},
title = {Dealing with Unknowns in Continual Learning for End-to-end Automatic
Speech Recognition},
booktitle = {Interspeech 2022, 23rd Annual Conference of the International Speech
Communication Association, Incheon, Korea, 18-22 September 2022},
pages = {1046--1050},
publisher = {{ISCA}},
year = {2022},
url = {https://doi.org/10.21437/Interspeech.2022-11139},
doi = {10.21437/INTERSPEECH.2022-11139},
timestamp = {Wed, 21 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/SustekSH22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/SadhuH22,
author = {Samik Sadhu and
Hynek Hermansky},
editor = {Hanseok Ko and
John H. L. Hansen},
title = {Complex Frequency Domain Linear Prediction: {A} Tool to Compute Modulation
Spectrum of Speech},
booktitle = {Interspeech 2022, 23rd Annual Conference of the International Speech
Communication Association, Incheon, Korea, 18-22 September 2022},
pages = {3208--3212},
publisher = {{ISCA}},
year = {2022},
url = {https://doi.org/10.21437/Interspeech.2022-11095},
doi = {10.21437/INTERSPEECH.2022-11095},
timestamp = {Wed, 21 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/SadhuH22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2203-13216,
author = {Samik Sadhu and
Hynek Hermansky},
title = {Complex Frequency Domain Linear Prediction: {A} Tool to Compute Modulation
Spectrum of Speech},
journal = {CoRR},
volume = {abs/2203.13216},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2203.13216},
doi = {10.48550/ARXIV.2203.13216},
eprinttype = {arXiv},
eprint = {2203.13216},
timestamp = {Tue, 29 Mar 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2203-13216.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2204-00065,
author = {Samik Sadhu and
Hynek Hermansky},
title = {Importance of Different Temporal Modulations of Speech: {A} Tale of
Two Perspectives},
journal = {CoRR},
volume = {abs/2204.00065},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2204.00065},
doi = {10.48550/ARXIV.2204.00065},
eprinttype = {arXiv},
eprint = {2204.00065},
timestamp = {Wed, 06 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2204-00065.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2210-00117,
author = {Samik Sadhu and
Hynek Hermansky},
title = {Blind Signal Dereverberation for Machine Speech Recognition},
journal = {CoRR},
volume = {abs/2210.00117},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2210.00117},
doi = {10.48550/ARXIV.2210.00117},
eprinttype = {arXiv},
eprint = {2210.00117},
timestamp = {Fri, 07 Oct 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2210-00117.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/SadhuH21,
author = {Samik Sadhu and
Hynek Hermansky},
editor = {Hynek Hermansky and
Honza Cernock{\'{y}} and
Luk{\'{a}}s Burget and
Lori Lamel and
Odette Scharenborg and
Petr Motl{\'{\i}}cek},
title = {Radically Old Way of Computing Spectra: Applications in End-to-End
{ASR}},
booktitle = {Interspeech 2021, 22nd Annual Conference of the International Speech
Communication Association, Brno, Czechia, 30 August - 3 September
2021},
pages = {1424--1428},
publisher = {{ISCA}},
year = {2021},
url = {https://doi.org/10.21437/Interspeech.2021-643},
doi = {10.21437/INTERSPEECH.2021-643},
timestamp = {Wed, 21 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/SadhuH21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/slt/LiSH21,
author = {Ruizhi Li and
Gregory Sell and
Hynek Hermansky},
title = {Two-Stage Augmentation and Adaptive {CTC} Fusion for Improved Robustness
of Multi-Stream end-to-end {ASR}},
booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen,
China, January 19-22, 2021},
pages = {229--235},
publisher = {{IEEE}},
year = {2021},
url = {https://doi.org/10.1109/SLT48900.2021.9383621},
doi = {10.1109/SLT48900.2021.9383621},
timestamp = {Thu, 08 Apr 2021 14:52:59 +0200},
biburl = {https://dblp.org/rec/conf/slt/LiSH21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@proceedings{DBLP:conf/interspeech/2021,
editor = {Hynek Hermansky and
Honza Cernock{\'{y}} and
Luk{\'{a}}s Burget and
Lori Lamel and
Odette Scharenborg and
Petr Motl{\'{\i}}cek},
title = {Interspeech 2021, 22nd Annual Conference of the International Speech
Communication Association, Brno, Czechia, 30 August - 3 September
2021},
publisher = {{ISCA}},
year = {2021},
url = {https://doi.org/10.21437/Interspeech.2021},
doi = {10.21437/INTERSPEECH.2021},
timestamp = {Mon, 14 Mar 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/interspeech/2021.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2102-03055,
author = {Ruizhi Li and
Gregory Sell and
Hynek Hermansky},
title = {Two-Stage Augmentation and Adaptive {CTC} Fusion for Improved Robustness
of Multi-Stream End-to-End {ASR}},
journal = {CoRR},
volume = {abs/2102.03055},
year = {2021},
url = {https://arxiv.org/abs/2102.03055},
eprinttype = {arXiv},
eprint = {2102.03055},
timestamp = {Wed, 10 Feb 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2102-03055.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2103-14129,
author = {Samik Sadhu and
Hynek Hermansky},
title = {Radically Old Way of Computing Spectra: Applications in End-to-End
{ASR}},
journal = {CoRR},
volume = {abs/2103.14129},
year = {2021},
url = {https://arxiv.org/abs/2103.14129},
eprinttype = {arXiv},
eprint = {2103.14129},
timestamp = {Wed, 07 Apr 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2103-14129.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/taslp/LiWMWHH20,
author = {Ruizhi Li and
Xiaofei Wang and
Sri Harish Mallidi and
Shinji Watanabe and
Takaaki Hori and
Hynek Hermansky},
title = {Multi-Stream End-to-End Speech Recognition},
journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.},
volume = {28},
pages = {646--655},
year = {2020},
url = {https://doi.org/10.1109/TASLP.2019.2959721},
doi = {10.1109/TASLP.2019.2959721},
timestamp = {Thu, 17 Sep 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/taslp/LiWMWHH20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/LiSW0H20,
author = {Ruizhi Li and
Gregory Sell and
Xiaofei Wang and
Shinji Watanabe and
Hynek Hermansky},
title = {A Practical Two-Stage Training Strategy for Multi-Stream End-to-End
Speech Recognition},
booktitle = {2020 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2020, Barcelona, Spain, May 4-8, 2020},
pages = {7014--7018},
publisher = {{IEEE}},
year = {2020},
url = {https://doi.org/10.1109/ICASSP40776.2020.9053455},
doi = {10.1109/ICASSP40776.2020.9053455},
timestamp = {Tue, 29 Dec 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/LiSW0H20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/SadhuH20,
author = {Samik Sadhu and
Hynek Hermansky},
editor = {Helen Meng and
Bo Xu and
Thomas Fang Zheng},
title = {Continual Learning in Automatic Speech Recognition},
booktitle = {Interspeech 2020, 21st Annual Conference of the International Speech
Communication Association, Virtual Event, Shanghai, China, 25-29 October
2020},
pages = {1246--1250},
publisher = {{ISCA}},
year = {2020},
url = {https://doi.org/10.21437/Interspeech.2020-2962},
doi = {10.21437/INTERSPEECH.2020-2962},
timestamp = {Fri, 29 Jan 2021 17:40:16 +0100},
biburl = {https://dblp.org/rec/conf/interspeech/SadhuH20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/GhahramaniHPHK20,
author = {Pegah Ghahramani and
Hossein Hadian and
Daniel Povey and
Hynek Hermansky and
Sanjeev Khudanpur},
editor = {Helen Meng and
Bo Xu and
Thomas Fang Zheng},
title = {An Alternative to MFCCs for {ASR}},
booktitle = {Interspeech 2020, 21st Annual Conference of the International Speech
Communication Association, Virtual Event, Shanghai, China, 25-29 October
2020},
pages = {1664--1667},
publisher = {{ISCA}},
year = {2020},
url = {https://doi.org/10.21437/Interspeech.2020-2690},
doi = {10.21437/INTERSPEECH.2020-2690},
timestamp = {Fri, 29 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/interspeech/GhahramaniHPHK20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/speech/MartinezGVHOM19,
author = {Angel Mario Castro Martinez and
Lukas Gerlach and
Guillermo Pay{\'{a}} Vay{\'{a}} and
Hynek Hermansky and
Jasper Ooster and
Bernd T. Meyer},
title = {DNN-based performance measures for predicting error rates in automatic
speech recognition and optimizing hearing aid parameters},
journal = {Speech Commun.},
volume = {106},
pages = {44--56},
year = {2019},
url = {https://doi.org/10.1016/j.specom.2018.11.006},
doi = {10.1016/J.SPECOM.2018.11.006},
timestamp = {Tue, 01 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/speech/MartinezGVHOM19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/speech/Hermansky19,
author = {Hynek Hermansky},
title = {Coding and decoding of messages in human speech communication: Implications
for machine recognition of speech},
journal = {Speech Commun.},
volume = {106},
pages = {112--117},
year = {2019},
url = {https://doi.org/10.1016/j.specom.2018.12.004},
doi = {10.1016/J.SPECOM.2018.12.004},
timestamp = {Sat, 22 Feb 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/speech/Hermansky19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/OndelLSH19,
author = {Lucas Ondel and
Ruizhi Li and
Gregory Sell and
Hynek Hermansky},
title = {Deriving Spectro-temporal Properties of Hearing from Speech Data},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2019, Brighton, United Kingdom, May 12-17, 2019},
pages = {411--415},
publisher = {{IEEE}},
year = {2019},
url = {https://doi.org/10.1109/ICASSP.2019.8682787},
doi = {10.1109/ICASSP.2019.8682787},
timestamp = {Wed, 16 Oct 2019 14:14:52 +0200},
biburl = {https://dblp.org/rec/conf/icassp/OndelLSH19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/YangOMH19,
author = {Jinyi Yang and
Lucas Ondel and
Vimal Manohar and
Hynek Hermansky},
title = {Towards Automatic Methods to Detect Errors in Transcriptions of Speech
Recordings},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2019, Brighton, United Kingdom, May 12-17, 2019},
pages = {3747--3751},
publisher = {{IEEE}},
year = {2019},
url = {https://doi.org/10.1109/ICASSP.2019.8683722},
doi = {10.1109/ICASSP.2019.8683722},
timestamp = {Sun, 30 Jun 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/YangOMH19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/SadhuLH19,
author = {Samik Sadhu and
Ruizhi Li and
Hynek Hermansky},
title = {M-vectors: Sub-band Based Energy Modulation Features for Multi-stream
Automatic Speech Recognition},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2019, Brighton, United Kingdom, May 12-17, 2019},
pages = {6545--6549},
publisher = {{IEEE}},
year = {2019},
url = {https://doi.org/10.1109/ICASSP.2019.8682710},
doi = {10.1109/ICASSP.2019.8682710},
timestamp = {Sun, 30 Jun 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/SadhuLH19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/WangLMHWH19,
author = {Xiaofei Wang and
Ruizhi Li and
Sri Harish Mallidi and
Takaaki Hori and
Shinji Watanabe and
Hynek Hermansky},
title = {Stream Attention-based Multi-array End-to-end Speech Recognition},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2019, Brighton, United Kingdom, May 12-17, 2019},
pages = {7105--7109},
publisher = {{IEEE}},
year = {2019},
url = {https://doi.org/10.1109/ICASSP.2019.8682650},
doi = {10.1109/ICASSP.2019.8682650},
timestamp = {Thu, 17 Sep 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/WangLMHWH19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/LiSH19,
author = {Ruizhi Li and
Gregory Sell and
Hynek Hermansky},
editor = {Gernot Kubin and
Zdravko Kacic},
title = {Performance Monitoring for End-to-End Speech Recognition},
booktitle = {Interspeech 2019, 20th Annual Conference of the International Speech
Communication Association, Graz, Austria, 15-19 September 2019},
pages = {2245--2249},
publisher = {{ISCA}},
year = {2019},
url = {https://doi.org/10.21437/Interspeech.2019-3137},
doi = {10.21437/INTERSPEECH.2019-3137},
timestamp = {Fri, 29 Jan 2021 17:41:10 +0100},
biburl = {https://dblp.org/rec/conf/interspeech/LiSH19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/WangYLSH19,
author = {Xiaofei Wang and
Jinyi Yang and
Ruizhi Li and
Samik Sadhu and
Hynek Hermansky},
editor = {Gernot Kubin and
Zdravko Kacic},
title = {Exploring Methods for the Automatic Detection of Errors in Manual
Transcription},
booktitle = {Interspeech 2019, 20th Annual Conference of the International Speech
Communication Association, Graz, Austria, 15-19 September 2019},
pages = {3003--3007},
publisher = {{ISCA}},
year = {2019},
url = {https://doi.org/10.21437/Interspeech.2019-1343},
doi = {10.21437/INTERSPEECH.2019-1343},
timestamp = {Fri, 29 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/interspeech/WangYLSH19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/SadhuH19,
author = {Samik Sadhu and
Hynek Hermansky},
editor = {Gernot Kubin and
Zdravko Kacic},
title = {Modulation Vectors as Robust Feature Representation for {ASR} in Domain
Mismatched Conditions},
booktitle = {Interspeech 2019, 20th Annual Conference of the International Speech
Communication Association, Graz, Austria, 15-19 September 2019},
pages = {3441--3445},
publisher = {{ISCA}},
year = {2019},
url = {https://doi.org/10.21437/Interspeech.2019-2723},
doi = {10.21437/INTERSPEECH.2019-2723},
timestamp = {Fri, 29 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/interspeech/SadhuH19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1904-04294,
author = {Xiaofei Wang and
Jinyi Yang and
Ruizhi Li and
Samik Sadhu and
Hynek Hermansky},
title = {Exploring Methods for the Automatic Detection of Errors in Manual
Transcription},
journal = {CoRR},
volume = {abs/1904.04294},
year = {2019},
url = {http://arxiv.org/abs/1904.04294},
eprinttype = {arXiv},
eprint = {1904.04294},
timestamp = {Thu, 17 Sep 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1904-04294.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1904-04896,
author = {Ruizhi Li and
Gregory Sell and
Hynek Hermansky},
title = {Performance Monitoring for End-to-End Speech Recognition},
journal = {CoRR},
volume = {abs/1904.04896},
year = {2019},
url = {http://arxiv.org/abs/1904.04896},
eprinttype = {arXiv},
eprint = {1904.04896},
timestamp = {Thu, 25 Apr 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1904-04896.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1906-08041,
author = {Ruizhi Li and
Xiaofei Wang and
Sri Harish Mallidi and
Shinji Watanabe and
Takaaki Hori and
Hynek Hermansky},
title = {Multi-Stream End-to-End Speech Recognition},
journal = {CoRR},
volume = {abs/1906.08041},
year = {2019},
url = {http://arxiv.org/abs/1906.08041},
eprinttype = {arXiv},
eprint = {1906.08041},
timestamp = {Thu, 17 Sep 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1906-08041.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1910-10671,
author = {Ruizhi Li and
Gregory Sell and
Xiaofei Wang and
Shinji Watanabe and
Hynek Hermansky},
title = {A practical two-stage training strategy for multi-stream end-to-end
speech recognition},
journal = {CoRR},
volume = {abs/1910.10671},
year = {2019},
url = {http://arxiv.org/abs/1910.10671},
eprinttype = {arXiv},
eprint = {1910.10671},
timestamp = {Thu, 17 Sep 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1910-10671.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/WangLH18,
author = {Xiaofei Wang and
Ruizhi Li and
Hynek Hermansky},
editor = {B. Yegnanarayana},
title = {Stream Attention for Distributed Multi-Microphone Speech Recognition},
booktitle = {Interspeech 2018, 19th Annual Conference of the International Speech
Communication Association, Hyderabad, India, 2-6 September 2018},
pages = {3033--3037},
publisher = {{ISCA}},
year = {2018},
url = {https://doi.org/10.21437/Interspeech.2018-1037},
doi = {10.21437/INTERSPEECH.2018-1037},
timestamp = {Fri, 21 May 2021 08:16:43 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/WangLH18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1811-04897,
author = {Ruizhi Li and
Xiaofei Wang and
Sri Harish Reddy Mallidi and
Takaaki Hori and
Shinji Watanabe and
Hynek Hermansky},
title = {Multi-encoder multi-resolution framework for end-to-end speech recognition},
journal = {CoRR},
volume = {abs/1811.04897},
year = {2018},
url = {http://arxiv.org/abs/1811.04897},
eprinttype = {arXiv},
eprint = {1811.04897},
timestamp = {Thu, 17 Sep 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1811-04897.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1811-04903,
author = {Xiaofei Wang and
Ruizhi Li and
Sri Harish Mallidi and
Takaaki Hori and
Shinji Watanabe and
Hynek Hermansky},
title = {Stream attention-based multi-array end-to-end speech recognition},
journal = {CoRR},
volume = {abs/1811.04903},
year = {2018},
url = {http://arxiv.org/abs/1811.04903},
eprinttype = {arXiv},
eprint = {1811.04903},
timestamp = {Thu, 17 Sep 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1811-04903.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/MeyerMKH17,
author = {Bernd T. Meyer and
Sri Harish Reddy Mallidi and
Hendrik Kayser and
Hynek Hermansky},
title = {Predicting error rates for unknown data in automatic speech recognition},
booktitle = {2017 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2017, New Orleans, LA, USA, March 5-9, 2017},
pages = {5330--5334},
publisher = {{IEEE}},
year = {2017},
url = {https://doi.org/10.1109/ICASSP.2017.7953174},
doi = {10.1109/ICASSP.2017.7953174},
timestamp = {Wed, 16 Oct 2019 14:14:52 +0200},
biburl = {https://dblp.org/rec/conf/icassp/MeyerMKH17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1711-11141,
author = {Xiaofei Wang and
Yonghong Yan and
Hynek Hermansky},
title = {Stream Attention for far-field multi-microphone {ASR}},
journal = {CoRR},
volume = {abs/1711.11141},
year = {2017},
url = {http://arxiv.org/abs/1711.11141},
eprinttype = {arXiv},
eprint = {1711.11141},
timestamp = {Thu, 17 Sep 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1711-11141.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/MallidiH16,
author = {Sri Harish Reddy Mallidi and
Hynek Hermansky},
title = {Novel neural network based fusion for multistream {ASR}},
booktitle = {2016 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2016, Shanghai, China, March 20-25, 2016},
pages = {5680--5684},
publisher = {{IEEE}},
year = {2016},
url = {https://doi.org/10.1109/ICASSP.2016.7472765},
doi = {10.1109/ICASSP.2016.7472765},
timestamp = {Wed, 16 Oct 2019 14:14:52 +0200},
biburl = {https://dblp.org/rec/conf/icassp/MallidiH16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icpr/OgawaMDCFH16,
author = {Tetsuji Ogawa and
Sri Harish Reddy Mallidi and
Emmanuel Dupoux and
Jordan Cohen and
Naomi H. Feldman and
Hynek Hermansky},
title = {A new efficient measure for accuracy prediction and its application
to multistream-based unsupervised adaptation},
booktitle = {23rd International Conference on Pattern Recognition, {ICPR} 2016,
Canc{\'{u}}n, Mexico, December 4-8, 2016},
pages = {2222--2227},
publisher = {{IEEE}},
year = {2016},
url = {https://doi.org/10.1109/ICPR.2016.7899966},
doi = {10.1109/ICPR.2016.7899966},
timestamp = {Wed, 16 Oct 2019 14:14:52 +0200},
biburl = {https://dblp.org/rec/conf/icpr/OgawaMDCFH16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/SpilleKHM16,
author = {Constantin Spille and
Hendrik Kayser and
Hynek Hermansky and
Bernd T. Meyer},
editor = {Nelson Morgan},
title = {Assessing Speech Quality in Speech-Aware Hearing Aids Based on Phoneme
Posteriorgrams},
booktitle = {Interspeech 2016, 17th Annual Conference of the International Speech
Communication Association, San Francisco, CA, USA, September 8-12,
2016},
pages = {1755--1759},
publisher = {{ISCA}},
year = {2016},
url = {https://doi.org/10.21437/Interspeech.2016-1318},
doi = {10.21437/INTERSPEECH.2016-1318},
timestamp = {Mon, 26 Jun 2023 16:43:56 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/SpilleKHM16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/MallidiH16,
author = {Sri Harish Reddy Mallidi and
Hynek Hermansky},
editor = {Nelson Morgan},
title = {A Framework for Practical Multistream {ASR}},
booktitle = {Interspeech 2016, 17th Annual Conference of the International Speech
Communication Association, San Francisco, CA, USA, September 8-12,
2016},
pages = {3474--3478},
publisher = {{ISCA}},
year = {2016},
url = {https://doi.org/10.21437/Interspeech.2016-619},
doi = {10.21437/INTERSPEECH.2016-619},
timestamp = {Fri, 29 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/interspeech/MallidiH16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/slt/MeyerMMVKH16,
author = {Bernd T. Meyer and
Sri Harish Reddy Mallidi and
Angel Mario Castro Martinez and
Guillermo Pay{\'{a}} Vay{\'{a}} and
Hendrik Kayser and
Hynek Hermansky},
title = {Performance monitoring for automatic speech recognition in noisy multi-channel
environments},
booktitle = {2016 {IEEE} Spoken Language Technology Workshop, {SLT} 2016, San Diego,
CA, USA, December 13-16, 2016},
pages = {50--56},
publisher = {{IEEE}},
year = {2016},
url = {https://doi.org/10.1109/SLT.2016.7846244},
doi = {10.1109/SLT.2016.7846244},
timestamp = {Wed, 16 Oct 2019 14:14:53 +0200},
biburl = {https://dblp.org/rec/conf/slt/MeyerMMVKH16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/asru/MallidiOH15,
author = {Sri Harish Reddy Mallidi and
Tetsuji Ogawa and
Hynek Hermansky},
title = {Uncertainty estimation of {DNN} classifiers},
booktitle = {2015 {IEEE} Workshop on Automatic Speech Recognition and Understanding,
{ASRU} 2015, Scottsdale, AZ, USA, December 13-17, 2015},
pages = {283--288},
publisher = {{IEEE}},
year = {2015},
url = {https://doi.org/10.1109/ASRU.2015.7404806},
doi = {10.1109/ASRU.2015.7404806},
timestamp = {Wed, 16 Oct 2019 14:14:51 +0200},
biburl = {https://dblp.org/rec/conf/asru/MallidiOH15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/asru/HsiaoMHKGBSCWCM15,
author = {Roger Hsiao and
Jeff Z. Ma and
William Hartmann and
Martin Karafi{\'{a}}t and
Frantisek Gr{\'{e}}zl and
Luk{\'{a}}s Burget and
Igor Sz{\"{o}}ke and
Jan Cernock{\'{y}} and
Shinji Watanabe and
Zhuo Chen and
Sri Harish Reddy Mallidi and
Hynek Hermansky and
Stavros Tsakalidis and
Richard M. Schwartz},
title = {Robust speech recognition in unknown reverberant and noisy conditions},
booktitle = {2015 {IEEE} Workshop on Automatic Speech Recognition and Understanding,
{ASRU} 2015, Scottsdale, AZ, USA, December 13-17, 2015},
pages = {533--538},
publisher = {{IEEE}},
year = {2015},
url = {https://doi.org/10.1109/ASRU.2015.7404841},
doi = {10.1109/ASRU.2015.7404841},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/asru/HsiaoMHKGBSCWCM15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/HermanskyBCDFGK15,
author = {Hynek Hermansky and
Luk{\'{a}}s Burget and
Jordan Cohen and
Emmanuel Dupoux and
Naomi Feldman and
John Godfrey and
Sanjeev Khudanpur and
Matthew Maciejewski and
Sri Harish Reddy Mallidi and
Anjali Menon and
Tetsuji Ogawa and
Vijayaditya Peddinti and
Richard C. Rose and
Richard M. Stern and
Matthew Wiesner and
Karel Vesel{\'{y}}},
title = {Towards machines that know when they do not know: Summary of work
done at 2014 Frederick Jelinek Memorial Workshop},
booktitle = {2015 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2015, South Brisbane, Queensland, Australia,
April 19-24, 2015},
pages = {5009--5013},
publisher = {{IEEE}},
year = {2015},
url = {https://doi.org/10.1109/ICASSP.2015.7178924},
doi = {10.1109/ICASSP.2015.7178924},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/HermanskyBCDFGK15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/PesanBHV15,
author = {Jan Pes{\'{a}}n and
Luk{\'{a}}s Burget and
Hynek Hermansky and
Karel Vesel{\'{y}}},
title = {{DNN} derived filters for processing of modulation spectrum of speech},
booktitle = {{INTERSPEECH} 2015, 16th Annual Conference of the International Speech
Communication Association, Dresden, Germany, September 6-10, 2015},
pages = {1908--1911},
publisher = {{ISCA}},
year = {2015},
url = {https://doi.org/10.21437/Interspeech.2015-421},
doi = {10.21437/INTERSPEECH.2015-421},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/PesanBHV15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/MallidiOVNH15,
author = {Sri Harish Reddy Mallidi and
Tetsuji Ogawa and
Karel Vesel{\'{y}} and
Phani S. Nidadavolu and
Hynek Hermansky},
title = {Autoencoder based multi-stream combination for noise robust speech
recognition},
booktitle = {{INTERSPEECH} 2015, 16th Annual Conference of the International Speech
Communication Association, Dresden, Germany, September 6-10, 2015},
pages = {3551--3555},
publisher = {{ISCA}},
year = {2015},
url = {https://doi.org/10.21437/Interspeech.2015-704},
doi = {10.21437/INTERSPEECH.2015-704},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/MallidiOVNH15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/taslp/GanapathyMH14,
author = {Sriram Ganapathy and
Sri Harish Reddy Mallidi and
Hynek Hermansky},
title = {Robust Feature Extraction Using Modulation Filtering of Autoregressive
Models},
journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.},
volume = {22},
number = {8},
pages = {1285--1295},
year = {2014},
url = {https://doi.org/10.1109/TASLP.2014.2329190},
doi = {10.1109/TASLP.2014.2329190},
timestamp = {Fri, 13 Mar 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/taslp/GanapathyMH14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/KintzleyJH14,
author = {Keith Kintzley and
Aren Jansen and
Hynek Hermansky},
title = {Featherweight phonetic keyword search for conversational speech},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2014, Florence, Italy, May 4-9, 2014},
pages = {7859--7863},
publisher = {{IEEE}},
year = {2014},
url = {https://doi.org/10.1109/ICASSP.2014.6855130},
doi = {10.1109/ICASSP.2014.6855130},
timestamp = {Wed, 16 Oct 2019 14:14:52 +0200},
biburl = {https://dblp.org/rec/conf/icassp/KintzleyJH14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/LiNH14,
author = {Feipeng Li and
Phani S. Nidadavolu and
Hynek Hermansky},
editor = {Haizhou Li and
Helen M. Meng and
Bin Ma and
Engsiong Chng and
Lei Xie},
title = {A long, deep and wide artificial neural net for robust speech recognition
in unknown noise},
booktitle = {{INTERSPEECH} 2014, 15th Annual Conference of the International Speech
Communication Association, Singapore, September 14-18, 2014},
pages = {358--362},
publisher = {{ISCA}},
year = {2014},
url = {https://doi.org/10.21437/Interspeech.2014-84},
doi = {10.21437/INTERSPEECH.2014-84},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/LiNH14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/SchatzPCBHD14,
author = {Thomas Schatz and
Vijayaditya Peddinti and
Xuan{-}Nga Cao and
Francis R. Bach and
Hynek Hermansky and
Emmanuel Dupoux},
editor = {Haizhou Li and
Helen M. Meng and
Bin Ma and
Engsiong Chng and
Lei Xie},
title = {Evaluating speech features with the minimal-pair {ABX} task {(II):}
resistance to noise},
booktitle = {{INTERSPEECH} 2014, 15th Annual Conference of the International Speech
Communication Association, Singapore, September 14-18, 2014},
pages = {915--919},
publisher = {{ISCA}},
year = {2014},
url = {https://doi.org/10.21437/Interspeech.2014-228},
doi = {10.21437/INTERSPEECH.2014-228},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/SchatzPCBHD14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/MahajanMH14,
author = {Nagaraj Mahajan and
Nima Mesgarani and
Hynek Hermansky},
editor = {Haizhou Li and
Helen M. Meng and
Bin Ma and
Engsiong Chng and
Lei Xie},
title = {Principal components of auditory spectro-temporal receptive fields},
booktitle = {{INTERSPEECH} 2014, 15th Annual Conference of the International Speech
Communication Association, Singapore, September 14-18, 2014},
pages = {1983--1987},
publisher = {{ISCA}},
year = {2014},
url = {https://doi.org/10.21437/Interspeech.2014-452},
doi = {10.21437/INTERSPEECH.2014-452},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/MahajanMH14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/pieee/Hermansky13,
author = {Hynek Hermansky},
title = {Multistream Recognition of Speech: Dealing With Unknown Unknowns},
journal = {Proc. {IEEE}},
volume = {101},
number = {5},
pages = {1076--1088},
year = {2013},
url = {https://doi.org/10.1109/JPROC.2012.2236871},
doi = {10.1109/JPROC.2012.2236871},
timestamp = {Fri, 02 Oct 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/pieee/Hermansky13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/pieee/HermanskyCS13,
author = {Hynek Hermansky and
Jordan R. Cohen and
Richard M. Stern},
title = {Perceptual Properties of Current Speech Recognition Technology},
journal = {Proc. {IEEE}},
volume = {101},
number = {9},
pages = {1968--1985},
year = {2013},
url = {https://doi.org/10.1109/JPROC.2013.2252316},
doi = {10.1109/JPROC.2013.2252316},
timestamp = {Fri, 02 Oct 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/pieee/HermanskyCS13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tnn/GarimellaH13,
author = {Sri Garimella and
Hynek Hermansky},
title = {Factor Analysis of Auto-Associative Neural Networks With Application
in Speaker Verification},
journal = {{IEEE} Trans. Neural Networks Learn. Syst.},
volume = {24},
number = {4},
pages = {522--528},
year = {2013},
url = {https://doi.org/10.1109/TNNLS.2012.2236652},
doi = {10.1109/TNNLS.2012.2236652},
timestamp = {Mon, 09 Mar 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/tnn/GarimellaH13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/ThomasSCH13,
author = {Samuel Thomas and
Michael L. Seltzer and
Kenneth Church and
Hynek Hermansky},
title = {Deep neural network features and semi-supervised training for low
resource speech recognition},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2013, Vancouver, BC, Canada, May 26-31, 2013},
pages = {6704--6708},
publisher = {{IEEE}},
year = {2013},
url = {https://doi.org/10.1109/ICASSP.2013.6638959},
doi = {10.1109/ICASSP.2013.6638959},
timestamp = {Mon, 26 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/ThomasSCH13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/PlchotMMDMCGHMMSSTTZZ13,
author = {Oldrich Plchot and
Spyros Matsoukas and
Pavel Matejka and
Najim Dehak and
Jeff Z. Ma and
Sandro Cumani and
Ondrej Glembek and
Hynek Hermansky and
Sri Harish Reddy Mallidi and
Nima Mesgarani and
Richard M. Schwartz and
Mehdi Soufifar and
Zheng{-}Hua Tan and
Samuel Thomas and
Bing Zhang and
Xinhui Zhou},
title = {Developing a speaker identification system for the {DARPA} {RATS}
project},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2013, Vancouver, BC, Canada, May 26-31, 2013},
pages = {6768--6772},
publisher = {{IEEE}},
year = {2013},
url = {https://doi.org/10.1109/ICASSP.2013.6638972},
doi = {10.1109/ICASSP.2013.6638972},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/PlchotMMDMCGHMMSSTTZZ13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/ClarkMJH13,
author = {Pascal Clark and
Sri Harish Reddy Mallidi and
Aren Jansen and
Hynek Hermansky},
title = {Frequency offset correction in speech without detecting pitch},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2013, Vancouver, BC, Canada, May 26-31, 2013},
pages = {7020--7024},
publisher = {{IEEE}},
year = {2013},
url = {https://doi.org/10.1109/ICASSP.2013.6639023},
doi = {10.1109/ICASSP.2013.6639023},
timestamp = {Fri, 19 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/ClarkMJH13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/PeddintiH13,
author = {Vijayaditya Peddinti and
Hynek Hermansky},
title = {Filter-bank optimization for Frequency Domain Linear Prediction},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2013, Vancouver, BC, Canada, May 26-31, 2013},
pages = {7102--7106},
publisher = {{IEEE}},
year = {2013},
url = {https://doi.org/10.1109/ICASSP.2013.6639040},
doi = {10.1109/ICASSP.2013.6639040},
timestamp = {Fri, 19 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/PeddintiH13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/LiH13a,
author = {Feipeng Li and
Hynek Hermansky},
title = {Effect of filter bandwidth and spectral sampling rate of analysis
filterbank on automatic phoneme recognition},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2013, Vancouver, BC, Canada, May 26-31, 2013},
pages = {7121--7124},
publisher = {{IEEE}},
year = {2013},
url = {https://doi.org/10.1109/ICASSP.2013.6639044},
doi = {10.1109/ICASSP.2013.6639044},
timestamp = {Fri, 19 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/LiH13a.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/HermanskyVP13,
author = {Hynek Hermansky and
Ehsan Variani and
Vijayaditya Peddinti},
title = {Mean temporal distance: Predicting {ASR} error from temporal properties
of speech signal},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2013, Vancouver, BC, Canada, May 26-31, 2013},
pages = {7423--7426},
publisher = {{IEEE}},
year = {2013},
url = {https://doi.org/10.1109/ICASSP.2013.6639105},
doi = {10.1109/ICASSP.2013.6639105},
timestamp = {Fri, 19 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/HermanskyVP13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/JansenTH13,
author = {Aren Jansen and
Samuel Thomas and
Hynek Hermansky},
title = {Weak top-down constraints for unsupervised acoustic model training},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2013, Vancouver, BC, Canada, May 26-31, 2013},
pages = {8091--8095},
publisher = {{IEEE}},
year = {2013},
url = {https://doi.org/10.1109/ICASSP.2013.6639241},
doi = {10.1109/ICASSP.2013.6639241},
timestamp = {Fri, 03 Jul 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/JansenTH13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/JansenDGJKCFHMRSCMVBBCDFHLLNPRST13,
author = {Aren Jansen and
Emmanuel Dupoux and
Sharon Goldwater and
Mark Johnson and
Sanjeev Khudanpur and
Kenneth Church and
Naomi Feldman and
Hynek Hermansky and
Florian Metze and
Richard C. Rose and
Mike Seltzer and
Pascal Clark and
Ian McGraw and
Balakrishnan Varadarajan and
Erin Bennett and
Benjamin B{\"{o}}rschinger and
Justin T. Chiu and
Ewan Dunbar and
Abdellah Fourtassi and
David Harwath and
Chia{-}ying Lee and
Keith D. Levin and
Atta Norouzian and
Vijayaditya Peddinti and
Rachael Richardson and
Thomas Schatz and
Samuel Thomas},
title = {A summary of the 2012 {JHU} {CLSP} workshop on zero resource speech
technologies and models of early language acquisition},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2013, Vancouver, BC, Canada, May 26-31, 2013},
pages = {8111--8115},
publisher = {{IEEE}},
year = {2013},
url = {https://doi.org/10.1109/ICASSP.2013.6639245},
doi = {10.1109/ICASSP.2013.6639245},
timestamp = {Mon, 26 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/JansenDGJKCFHMRSCMVBBCDFHLLNPRST13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/MaZMMLH13,
author = {Jeff Z. Ma and
Bing Zhang and
Spyros Matsoukas and
Sri Harish Reddy Mallidi and
Feipeng Li and
Hynek Hermansky},
editor = {Fr{\'{e}}d{\'{e}}ric Bimbot and
Christophe Cerisara and
C{\'{e}}cile Fougeron and
Guillaume Gravier and
Lori Lamel and
Fran{\c{c}}ois Pellegrino and
Pascal Perrier},
title = {Improvements in language identification on the {RATS} noisy speech
corpus},
booktitle = {{INTERSPEECH} 2013, 14th Annual Conference of the International Speech
Communication Association, Lyon, France, August 25-29, 2013},
pages = {69--73},
publisher = {{ISCA}},
year = {2013},
url = {https://doi.org/10.21437/Interspeech.2013-40},
doi = {10.21437/INTERSPEECH.2013-40},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/MaZMMLH13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/KintzleyJH13,
author = {Keith Kintzley and
Aren Jansen and
Hynek Hermansky},
editor = {Fr{\'{e}}d{\'{e}}ric Bimbot and
Christophe Cerisara and
C{\'{e}}cile Fougeron and
Guillaume Gravier and
Lori Lamel and
Fran{\c{c}}ois Pellegrino and
Pascal Perrier},
title = {Text-to-speech inspired duration modeling for improved whole-word
acoustic models},
booktitle = {{INTERSPEECH} 2013, 14th Annual Conference of the International Speech
Communication Association, Lyon, France, August 25-29, 2013},
pages = {1253--1257},
publisher = {{ISCA}},
year = {2013},
url = {https://doi.org/10.21437/Interspeech.2013-337},
doi = {10.21437/INTERSPEECH.2013-337},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/KintzleyJH13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/SchatzPBJHD13,
author = {Thomas Schatz and
Vijayaditya Peddinti and
Francis R. Bach and
Aren Jansen and
Hynek Hermansky and
Emmanuel Dupoux},
editor = {Fr{\'{e}}d{\'{e}}ric Bimbot and
Christophe Cerisara and
C{\'{e}}cile Fougeron and
Guillaume Gravier and
Lori Lamel and
Fran{\c{c}}ois Pellegrino and
Pascal Perrier},
title = {Evaluating speech features with the minimal-pair {ABX} task: analysis
of the classical {MFC/PLP} pipeline},
booktitle = {{INTERSPEECH} 2013, 14th Annual Conference of the International Speech
Communication Association, Lyon, France, August 25-29, 2013},
pages = {1781--1785},
publisher = {{ISCA}},
year = {2013},
url = {https://doi.org/10.21437/Interspeech.2013-441},
doi = {10.21437/INTERSPEECH.2013-441},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/SchatzPBJHD13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/VarianiLH13,
author = {Ehsan Variani and
Feipeng Li and
Hynek Hermansky},
editor = {Fr{\'{e}}d{\'{e}}ric Bimbot and
Christophe Cerisara and
C{\'{e}}cile Fougeron and
Guillaume Gravier and
Lori Lamel and
Fran{\c{c}}ois Pellegrino and
Pascal Perrier},
title = {Multi-stream recognition of noisy speech with performance monitoring},
booktitle = {{INTERSPEECH} 2013, 14th Annual Conference of the International Speech
Communication Association, Lyon, France, August 25-29, 2013},
pages = {2978--2981},
publisher = {{ISCA}},
year = {2013},
url = {https://doi.org/10.21437/Interspeech.2013-273},
doi = {10.21437/INTERSPEECH.2013-273},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/VarianiLH13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/OgawaLH13,
author = {Tetsuji Ogawa and
Feipeng Li and
Hynek Hermansky},
editor = {Fr{\'{e}}d{\'{e}}ric Bimbot and
Christophe Cerisara and
C{\'{e}}cile Fougeron and
Guillaume Gravier and
Lori Lamel and
Fran{\c{c}}ois Pellegrino and
Pascal Perrier},
title = {Stream selection and integration in multistream {ASR} using GMM-based
performance monitoring},
booktitle = {{INTERSPEECH} 2013, 14th Annual Conference of the International Speech
Communication Association, Lyon, France, August 25-29, 2013},
pages = {3332--3336},
publisher = {{ISCA}},
year = {2013},
url = {https://doi.org/10.21437/Interspeech.2013-737},
doi = {10.21437/INTERSPEECH.2013-737},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/OgawaLH13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/MallidiGH13,
author = {Sri Harish Reddy Mallidi and
Sriram Ganapathy and
Hynek Hermansky},
editor = {Fr{\'{e}}d{\'{e}}ric Bimbot and
Christophe Cerisara and
C{\'{e}}cile Fougeron and
Guillaume Gravier and
Lori Lamel and
Fran{\c{c}}ois Pellegrino and
Pascal Perrier},
title = {Robust speaker recognition using spectro-temporal autoregressive models},
booktitle = {{INTERSPEECH} 2013, 14th Annual Conference of the International Speech
Communication Association, Lyon, France, August 25-29, 2013},
pages = {3689--3693},
publisher = {{ISCA}},
year = {2013},
url = {https://doi.org/10.21437/Interspeech.2013-692},
doi = {10.21437/INTERSPEECH.2013-692},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/MallidiGH13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/tsd/Hermansky13,
author = {Hynek Hermansky},
editor = {Ivan Habernal and
V{\'{a}}clav Matousek},
title = {Long, Deep and Wide Artificial Neural Nets for Dealing with Unexpected
Noise in Machine Recognition of Speech},
booktitle = {Text, Speech, and Dialogue - 16th International Conference, {TSD}
2013, Pilsen, Czech Republic, September 1-5, 2013. Proceedings},
series = {Lecture Notes in Computer Science},
volume = {8082},
pages = {14--21},
publisher = {Springer},
year = {2013},
url = {https://doi.org/10.1007/978-3-642-40585-3\_2},
doi = {10.1007/978-3-642-40585-3\_2},
timestamp = {Tue, 14 May 2019 10:00:45 +0200},
biburl = {https://dblp.org/rec/conf/tsd/Hermansky13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/pami/WeinshallZHKOABGNPHP12,
author = {Daphna Weinshall and
Alon Zweig and
Hynek Hermansky and
Stefan Kombrink and
Frank W. Ohl and
J{\"{o}}rn Anem{\"{u}}ller and
J{\"{o}}rg{-}Hendrik Bach and
Luc Van Gool and
Fabian Nater and
Tom{\'{a}}s Pajdla and
Michal Havlena and
Misha Pavel},
title = {Beyond Novelty Detection: Incongruent Events, When General and Specific
Classifiers Disagree},
journal = {{IEEE} Trans. Pattern Anal. Mach. Intell.},
volume = {34},
number = {10},
pages = {1886--1901},
year = {2012},
url = {https://doi.org/10.1109/TPAMI.2011.279},
doi = {10.1109/TPAMI.2011.279},
timestamp = {Sat, 19 Oct 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/pami/WeinshallZHKOABGNPHP12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/speech/IkbalMHM12,
author = {Shajith Ikbal and
Hemant Misra and
Hynek Hermansky and
Mathew Magimai{-}Doss},
title = {Phase AutoCorrelation {(PAC)} features for noise robust speech recognition},
journal = {Speech Commun.},
volume = {54},
number = {7},
pages = {867--880},
year = {2012},
url = {https://doi.org/10.1016/j.specom.2012.02.005},
doi = {10.1016/J.SPECOM.2012.02.005},
timestamp = {Mon, 26 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/speech/IkbalMHM12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/spl/GarimellaMH12,
author = {Sri Garimella and
Sri Harish Reddy Mallidi and
Hynek Hermansky},
title = {Regularized Auto-Associative Neural Networks for Speaker Verification},
journal = {{IEEE} Signal Process. Lett.},
volume = {19},
number = {12},
pages = {841--844},
year = {2012},
url = {https://doi.org/10.1109/LSP.2012.2221706},
doi = {10.1109/LSP.2012.2221706},
timestamp = {Sun, 28 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/spl/GarimellaMH12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/taslp/SivaramH12,
author = {Garimella S. V. S. Sivaram and
Hynek Hermansky},
title = {Sparse Multilayer Perceptron for Phoneme Recognition},
journal = {{IEEE} Trans. Speech Audio Process.},
volume = {20},
number = {1},
pages = {23--29},
year = {2012},
url = {https://doi.org/10.1109/TASL.2011.2129510},
doi = {10.1109/TASL.2011.2129510},
timestamp = {Sun, 17 May 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/taslp/SivaramH12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ITGspeech/HirschGH12,
author = {Hans{-}G{\"{u}}nter Hirsch and
Sriram Ganapathy and
Hynek Hermansky},
title = {Comparison of Different Approaches for Speech Recognition in Hands-free
Mode},
booktitle = {Proceedings of the 10th {ITG} Conference on Speech Communication,
Braunschweig, Germany, September 26-28, 2012},
pages = {1--4},
publisher = {{IEEE}},
year = {2012},
url = {https://ieeexplore.ieee.org/document/6309623/},
timestamp = {Wed, 11 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ITGspeech/HirschGH12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/Garcia-RomeroZZSLGTNSMMJRMEHSD12,
author = {Daniel Garcia{-}Romero and
Xinhui Zhou and
Dmitry N. Zotkin and
Balaji Vasan Srinivasan and
Yuancheng Luo and
Sriram Ganapathy and
Samuel Thomas and
Sridhar Krishna Nemala and
Garimella S. V. S. Sivaram and
Majid Mirbagheri and
Sri Harish Reddy Mallidi and
Thomas Janu and
Padmanabhan Rajan and
Nima Mesgarani and
Mounya Elhilali and
Hynek Hermansky and
Shihab A. Shamma and
Ramani Duraiswami},
title = {The {UMD-JHU} 2011 speaker recognition system},
booktitle = {2012 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2012, Kyoto, Japan, March 25-30, 2012},
pages = {4229--4232},
publisher = {{IEEE}},
year = {2012},
url = {https://doi.org/10.1109/ICASSP.2012.6288852},
doi = {10.1109/ICASSP.2012.6288852},
timestamp = {Tue, 21 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/Garcia-RomeroZZSLGTNSMMJRMEHSD12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/ThomasGH12,
author = {Samuel Thomas and
Sriram Ganapathy and
Hynek Hermansky},
title = {Multilingual {MLP} features for low-resource {LVCSR} systems},
booktitle = {2012 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2012, Kyoto, Japan, March 25-30, 2012},
pages = {4269--4272},
publisher = {{IEEE}},
year = {2012},
url = {https://doi.org/10.1109/ICASSP.2012.6288862},
doi = {10.1109/ICASSP.2012.6288862},
timestamp = {Fri, 03 Jul 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/ThomasGH12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/KintzleyJH12,
author = {Keith Kintzley and
Aren Jansen and
Hynek Hermansky},
title = {{MAP} Estimation of Whole-Word Acoustic Models with Dictionary Priors},
booktitle = {{INTERSPEECH} 2012, 13th Annual Conference of the International Speech
Communication Association, Portland, Oregon, USA, September 9-13,
2012},
pages = {787--790},
publisher = {{ISCA}},
year = {2012},
url = {https://doi.org/10.21437/Interspeech.2012-241},
doi = {10.21437/INTERSPEECH.2012-241},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/KintzleyJH12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/ThomasGJH12,
author = {Samuel Thomas and
Sriram Ganapathy and
Aren Jansen and
Hynek Hermansky},
title = {Data-driven Posterior Features for Low Resource Speech Recognition
Applications},
booktitle = {{INTERSPEECH} 2012, 13th Annual Conference of the International Speech
Communication Association, Portland, Oregon, USA, September 9-13,
2012},
pages = {791--794},
publisher = {{ISCA}},
year = {2012},
url = {https://doi.org/10.21437/Interspeech.2012-242},
doi = {10.21437/INTERSPEECH.2012-242},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/ThomasGJH12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/JansenTH12,
author = {Aren Jansen and
Samuel Thomas and
Hynek Hermansky},
title = {Intrinsic Spectral Analysis for Zero and High Resource Speech Recognition},
booktitle = {{INTERSPEECH} 2012, 13th Annual Conference of the International Speech
Communication Association, Portland, Oregon, USA, September 9-13,
2012},
pages = {879--882},
publisher = {{ISCA}},
year = {2012},
url = {https://doi.org/10.21437/Interspeech.2012-266},
doi = {10.21437/INTERSPEECH.2012-266},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/JansenTH12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/VarianiH12,
author = {Ehsan Variani and
Hynek Hermansky},
title = {Estimating Classifier Performance in Unknown Noise},
booktitle = {{INTERSPEECH} 2012, 13th Annual Conference of the International Speech
Communication Association, Portland, Oregon, USA, September 9-13,
2012},
pages = {1800--1803},
publisher = {{ISCA}},
year = {2012},
url = {https://doi.org/10.21437/Interspeech.2012-490},
doi = {10.21437/INTERSPEECH.2012-490},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/VarianiH12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/LiMH12,
author = {Feipeng Li and
Sri Harish Reddy Mallidi and
Hynek Hermansky},
title = {Phone recognition in critical bands using sub-band temporal modulations},
booktitle = {{INTERSPEECH} 2012, 13th Annual Conference of the International Speech
Communication Association, Portland, Oregon, USA, September 9-13,
2012},
pages = {1816--1819},
publisher = {{ISCA}},
year = {2012},
url = {https://doi.org/10.21437/Interspeech.2012-494},
doi = {10.21437/INTERSPEECH.2012-494},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/LiMH12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/GanapathyH12,
author = {Sriram Ganapathy and
Hynek Hermansky},
title = {Analysis of Temporal Resolution in Frequency Domain Linear Prediction},
booktitle = {{INTERSPEECH} 2012, 13th Annual Conference of the International Speech
Communication Association, Portland, Oregon, USA, September 9-13,
2012},
pages = {1828--1831},
publisher = {{ISCA}},
year = {2012},
url = {https://doi.org/10.21437/Interspeech.2012-497},
doi = {10.21437/INTERSPEECH.2012-497},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/GanapathyH12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/ThomasMJHMZSNZNM12,
author = {Samuel Thomas and
Sri Harish Reddy Mallidi and
Thomas Janu and
Hynek Hermansky and
Nima Mesgarani and
Xinhui Zhou and
Shihab A. Shamma and
Tim Ng and
Bing Zhang and
Long Nguyen and
Spyros Matsoukas},
title = {Acoustic and Data-driven Features for Robust Speech Activity Detection},
booktitle = {{INTERSPEECH} 2012, 13th Annual Conference of the International Speech
Communication Association, Portland, Oregon, USA, September 9-13,
2012},
pages = {1985--1988},
publisher = {{ISCA}},
year = {2012},
url = {https://doi.org/10.21437/Interspeech.2012-531},
doi = {10.21437/INTERSPEECH.2012-531},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/ThomasMJHMZSNZNM12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/KintzleyJCH12,
author = {Keith Kintzley and
Aren Jansen and
Kenneth Church and
Hynek Hermansky},
title = {Inverting the Point Process Model for Fast Phonetic Keyword Search},
booktitle = {{INTERSPEECH} 2012, 13th Annual Conference of the International Speech
Communication Association, Portland, Oregon, USA, September 9-13,
2012},
pages = {2438--2441},
publisher = {{ISCA}},
year = {2012},
url = {https://doi.org/10.21437/Interspeech.2012-638},
doi = {10.21437/INTERSPEECH.2012-638},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/KintzleyJCH12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/odyssey/GarimellaH12,
author = {Sri Garimella and
Hynek Hermansky},
editor = {Haizhou Li and
Bin Ma and
Kong{-}Aik Lee},
title = {Factor analysis of mixture of auto-associative neural networks for
speaker verification},
booktitle = {Odyssey 2012: The Speaker and Language Recognition Workshop, Singapore,
June 25-28, 2012},
pages = {92--97},
publisher = {{ISCA}},
year = {2012},
url = {http://www.isca-speech.org/archive/odyssey\_2012/od12\_092.html},
timestamp = {Mon, 13 Mar 2023 16:58:28 +0100},
biburl = {https://dblp.org/rec/conf/odyssey/GarimellaH12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/odyssey/ThomasMGH12,
author = {Samuel Thomas and
Sri Harish Reddy Mallidi and
Sriram Ganapathy and
Hynek Hermansky},
editor = {Haizhou Li and
Bin Ma and
Kong{-}Aik Lee},
title = {Adaptation transforms of auto-associative neural networks as features
for speaker verification},
booktitle = {Odyssey 2012: The Speaker and Language Recognition Workshop, Singapore,
June 25-28, 2012},
pages = {98--104},
publisher = {{ISCA}},
year = {2012},
url = {http://www.isca-speech.org/archive/odyssey\_2012/od12\_098.html},
timestamp = {Fri, 03 Jul 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/odyssey/ThomasMGH12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/odyssey/GanapathyTH12,
author = {Sriram Ganapathy and
Samuel Thomas and
Hynek Hermansky},
editor = {Haizhou Li and
Bin Ma and
Kong{-}Aik Lee},
title = {Feature extraction using 2-d autoregressive models for speaker recognition},
booktitle = {Odyssey 2012: The Speaker and Language Recognition Workshop, Singapore,
June 25-28, 2012},
pages = {229--235},
publisher = {{ISCA}},
year = {2012},
url = {http://www.isca-speech.org/archive/odyssey\_2012/od12\_229.html},
timestamp = {Tue, 16 Nov 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/odyssey/GanapathyTH12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@incollection{DBLP:series/sci/AnemullerCHOPPGVWW12,
author = {J{\"{o}}rn Anem{\"{u}}ller and
Barbara Caputo and
Hynek Hermansky and
Frank W. Ohl and
Tom{\'{a}}s Pajdla and
Misha Pavel and
Luc Van Gool and
Rufin Vogels and
Stefan Wabnik and
Daphna Weinshall},
editor = {Daphna Weinshall and
J{\"{o}}rn Anem{\"{u}}ller and
Luc Van Gool},
title = {{DIRAC:} Detection and Identification of Rare Audio-Visual Events},
booktitle = {Detection and Identification of Rare Audiovisual Cues},
series = {Studies in Computational Intelligence},
volume = {384},
pages = {3--35},
publisher = {Springer},
year = {2012},
url = {https://doi.org/10.1007/978-3-642-24034-8\_1},
doi = {10.1007/978-3-642-24034-8\_1},
timestamp = {Mon, 22 Jul 2019 18:47:52 +0200},
biburl = {https://dblp.org/rec/series/sci/AnemullerCHOPPGVWW12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/taslp/PintoSMHB11,
author = {Joel Pinto and
Garimella S. V. S. Sivaram and
Mathew Magimai{-}Doss and
Hynek Hermansky and
Herv{\'{e}} Bourlard},
title = {Analysis of MLP-Based Hierarchical Phoneme Posterior Probability Estimator},
journal = {{IEEE} Trans. Speech Audio Process.},
volume = {19},
number = {2},
pages = {225--241},
year = {2011},
url = {https://doi.org/10.1109/TASL.2010.2045943},
doi = {10.1109/TASL.2010.2045943},
timestamp = {Sun, 17 May 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/taslp/PintoSMHB11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/ThomasNZH11,
author = {Samuel Thomas and
Patrick Nguyen and
Geoffrey Zweig and
Hynek Hermansky},
title = {{MLP} based phoneme detectors for Automatic Speech Recognition},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing, {ICASSP} 2011, May 22-27, 2011, Prague Congress
Center, Prague, Czech Republic},
pages = {5024--5027},
publisher = {{IEEE}},
year = {2011},
url = {https://doi.org/10.1109/ICASSP.2011.5947485},
doi = {10.1109/ICASSP.2011.5947485},
timestamp = {Fri, 03 Jul 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/ThomasNZH11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/ZweigNCDACSWSHKJTSBK11,
author = {Geoffrey Zweig and
Patrick Nguyen and
Dirk Van Compernolle and
Kris Demuynck and
Les E. Atlas and
Pascal Clark and
Gregory Sell and
Meihong Wang and
Fei Sha and
Hynek Hermansky and
Damianos G. Karakos and
Aren Jansen and
Samuel Thomas and
Sivaram G. S. V. S. and
Samuel R. Bowman and
Justine T. Kao},
title = {Speech recognitionwith segmental conditional random fields: {A} summary
of the {JHU} {CLSP} 2010 Summer Workshop},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing, {ICASSP} 2011, May 22-27, 2011, Prague Congress
Center, Prague, Czech Republic},
pages = {5044--5047},
publisher = {{IEEE}},
year = {2011},
url = {https://doi.org/10.1109/ICASSP.2011.5947490},
doi = {10.1109/ICASSP.2011.5947490},
timestamp = {Fri, 03 Jul 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/ZweigNCDACSWSHKJTSBK11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/SivaramH11,
author = {Garimella S. V. S. Sivaram and
Hynek Hermansky},
title = {Multilayer perceptron with sparse hidden outputs for phoneme recognition},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing, {ICASSP} 2011, May 22-27, 2011, Prague Congress
Center, Prague, Czech Republic},
pages = {5336--5339},
publisher = {{IEEE}},
year = {2011},
url = {https://doi.org/10.1109/ICASSP.2011.5947563},
doi = {10.1109/ICASSP.2011.5947563},
timestamp = {Fri, 19 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/SivaramH11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/MallidiGH11,
author = {Sri Harish Reddy Mallidi and
Sriram Ganapathy and
Hynek Hermansky},
title = {Modulation Spectrum Analysis for Recognition of Reverberant Speech},
booktitle = {{INTERSPEECH} 2011, 12th Annual Conference of the International Speech
Communication Association, Florence, Italy, August 27-31, 2011},
pages = {189--192},
publisher = {{ISCA}},
year = {2011},
url = {https://doi.org/10.21437/Interspeech.2011-79},
doi = {10.21437/INTERSPEECH.2011-79},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/MallidiGH11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/CarlinTJH11,
author = {Michael A. Carlin and
Samuel Thomas and
Aren Jansen and
Hynek Hermansky},
title = {Rapid Evaluation of Speech Representations for Spoken Term Discovery},
booktitle = {{INTERSPEECH} 2011, 12th Annual Conference of the International Speech
Communication Association, Florence, Italy, August 27-31, 2011},
pages = {821--824},
publisher = {{ISCA}},
year = {2011},
url = {https://doi.org/10.21437/Interspeech.2011-304},
doi = {10.21437/INTERSPEECH.2011-304},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/CarlinTJH11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/KintzleyJH11,
author = {Keith Kintzley and
Aren Jansen and
Hynek Hermansky},
title = {Event Selection from Phone Posteriorgrams Using Matched Filters},
booktitle = {{INTERSPEECH} 2011, 12th Annual Conference of the International Speech
Communication Association, Florence, Italy, August 27-31, 2011},
pages = {1905--1908},
publisher = {{ISCA}},
year = {2011},
url = {https://doi.org/10.21437/Interspeech.2011-354},
doi = {10.21437/INTERSPEECH.2011-354},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/KintzleyJH11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/MesgaraniTH11,
author = {Nima Mesgarani and
Samuel Thomas and
Hynek Hermansky},
title = {Adaptive Stream Fusion in Multistream Recognition of Speech},
booktitle = {{INTERSPEECH} 2011, 12th Annual Conference of the International Speech
Communication Association, Florence, Italy, August 27-31, 2011},
pages = {2329--2332},
publisher = {{ISCA}},
year = {2011},
url = {https://doi.org/10.21437/Interspeech.2011-618},
doi = {10.21437/INTERSPEECH.2011-618},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/MesgaraniTH11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/SivaramTH11,
author = {Garimella S. V. S. Sivaram and
Samuel Thomas and
Hynek Hermansky},
title = {Mixture of Auto-Associative Neural Networks for Speaker Verification},
booktitle = {{INTERSPEECH} 2011, 12th Annual Conference of the International Speech
Communication Association, Florence, Italy, August 27-31, 2011},
pages = {2381--2384},
publisher = {{ISCA}},
year = {2011},
url = {https://doi.org/10.21437/Interspeech.2011-68},
doi = {10.21437/INTERSPEECH.2011-68},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/SivaramTH11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/mlslp/HermanskyMT11,
author = {Hynek Hermansky and
Nima Mesgarani and
Samuel Thomas},
title = {Performance monitoring for robustness in automatic recognition of
speechi},
booktitle = {2011 Symposium on Machine Learning in Speech and Language Processing,
{MLSLP} 2011, Bellevue, WA, USA, June 27, 2011},
pages = {31--34},
publisher = {{ISCA}},
year = {2011},
url = {http://www.isca-speech.org/archive/mlslp\_2011/ml11\_031.html},
timestamp = {Tue, 16 Nov 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/mlslp/HermanskyMT11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/tsd/Hermansky11,
author = {Hynek Hermansky},
editor = {Ivan Habernal and
V{\'{a}}clav Matousek},
title = {Dealing with Unexpected Words in Automatic Recognition of Speech},
booktitle = {Text, Speech and Dialogue - 14th International Conference, {TSD} 2011,
Pilsen, Czech Republic, September 1-5, 2011. Proceedings},
series = {Lecture Notes in Computer Science},
volume = {6836},
pages = {1--15},
publisher = {Springer},
year = {2011},
url = {https://doi.org/10.1007/978-3-642-23538-2\_1},
doi = {10.1007/978-3-642-23538-2\_1},
timestamp = {Tue, 14 May 2019 10:00:45 +0200},
biburl = {https://dblp.org/rec/conf/tsd/Hermansky11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/waspaa/GanapathyRH11,
author = {Sriram Ganapathy and
Padmanabhan Rajan and
Hynek Hermansky},
title = {Multi-layer perceptron based speech activity detection for speaker
verification},
booktitle = {{IEEE} Workshop on Applications of Signal Processing to Audio and
Acoustics, {WASPAA} 2011, New Paltz, NY, USA, October 16-19, 2011},
pages = {321--324},
publisher = {{IEEE}},
year = {2011},
url = {https://doi.org/10.1109/ASPAA.2011.6082323},
doi = {10.1109/ASPAA.2011.6082323},
timestamp = {Wed, 16 Oct 2019 14:14:57 +0200},
biburl = {https://dblp.org/rec/conf/waspaa/GanapathyRH11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ejasmp/MotlicekGHG10,
author = {Petr Motl{\'{\i}}cek and
Sriram Ganapathy and
Hynek Hermansky and
Harinath Garudadri},
title = {Wide-Band Audio Coding Based on Frequency-Domain Linear Prediction},
journal = {{EURASIP} J. Audio Speech Music. Process.},
volume = {2010},
year = {2010},
url = {https://doi.org/10.1155/2010/856280},
doi = {10.1155/2010/856280},
timestamp = {Tue, 29 Sep 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ejasmp/MotlicekGHG10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/spl/SivaramNMH10,
author = {Garimella S. V. S. Sivaram and
Sridhar Krishna Nemala and
Nima Mesgarani and
Hynek Hermansky},
title = {Data-Driven and Feedback Based Spectro-Temporal Features for Speech
Recognition},
journal = {{IEEE} Signal Process. Lett.},
volume = {17},
number = {11},
pages = {957--960},
year = {2010},
url = {https://doi.org/10.1109/LSP.2010.2079930},
doi = {10.1109/LSP.2010.2079930},
timestamp = {Sun, 28 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/spl/SivaramNMH10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/taslp/GanapathyMH10,
author = {Sriram Ganapathy and
Petr Motl{\'{\i}}cek and
Hynek Hermansky},
title = {Autoregressive Models of Amplitude Modulations in Audio Compression},
journal = {{IEEE} Trans. Speech Audio Process.},
volume = {18},
number = {6},
pages = {1624--1631},
year = {2010},
url = {https://doi.org/10.1109/TASL.2009.2038813},
doi = {10.1109/TASL.2009.2038813},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/taslp/GanapathyMH10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/GanapathyTH10,
author = {Sriram Ganapathy and
Samuel Thomas and
Hynek Hermansky},
title = {Robust spectro-temporal features based on autoregressive models of
Hilbert envelopes},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing, {ICASSP} 2010, 14-19 March 2010, Sheraton Dallas
Hotel, Dallas, Texas, {USA}},
pages = {4286--4289},
publisher = {{IEEE}},
year = {2010},
url = {https://doi.org/10.1109/ICASSP.2010.5495668},
doi = {10.1109/ICASSP.2010.5495668},
timestamp = {Fri, 03 Jul 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/GanapathyTH10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/SivaramNETH10,
author = {Garimella S. V. S. Sivaram and
Sridhar Krishna Nemala and
Mounya Elhilali and
Trac D. Tran and
Hynek Hermansky},
title = {Sparse coding for speech recognition},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing, {ICASSP} 2010, 14-19 March 2010, Sheraton Dallas
Hotel, Dallas, Texas, {USA}},
pages = {4346--4349},
publisher = {{IEEE}},
year = {2010},
url = {https://doi.org/10.1109/ICASSP.2010.5495649},
doi = {10.1109/ICASSP.2010.5495649},
timestamp = {Sun, 04 Jun 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/SivaramNETH10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/GanapathyTH10a,
author = {Sriram Ganapathy and
Samuel Thomas and
Hynek Hermansky},
title = {Comparison of modulation features for phoneme recognition},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing, {ICASSP} 2010, 14-19 March 2010, Sheraton Dallas
Hotel, Dallas, Texas, {USA}},
pages = {5038--5041},
publisher = {{IEEE}},
year = {2010},
url = {https://doi.org/10.1109/ICASSP.2010.5495057},
doi = {10.1109/ICASSP.2010.5495057},
timestamp = {Fri, 03 Jul 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/GanapathyTH10a.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/Hermansky10,
author = {Hynek Hermansky},
title = {History of modulation spectrum in {ASR}},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing, {ICASSP} 2010, 14-19 March 2010, Sheraton Dallas
Hotel, Dallas, Texas, {USA}},
pages = {5458--5461},
publisher = {{IEEE}},
year = {2010},
url = {https://doi.org/10.1109/ICASSP.2010.5494907},
doi = {10.1109/ICASSP.2010.5494907},
timestamp = {Fri, 19 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/Hermansky10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/MesgaraniTH10,
author = {Nima Mesgarani and
Samuel Thomas and
Hynek Hermansky},
editor = {Takao Kobayashi and
Keikichi Hirose and
Satoshi Nakamura},
title = {A multistream multiresolution framework for phoneme recognition},
booktitle = {{INTERSPEECH} 2010, 11th Annual Conference of the International Speech
Communication Association, Makuhari, Chiba, Japan, September 26-30,
2010},
pages = {318--321},
publisher = {{ISCA}},
year = {2010},
url = {https://doi.org/10.21437/Interspeech.2010-120},
doi = {10.21437/INTERSPEECH.2010-120},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/MesgaraniTH10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/ThomasGH10,
author = {Samuel Thomas and
Sriram Ganapathy and
Hynek Hermansky},
editor = {Takao Kobayashi and
Keikichi Hirose and
Satoshi Nakamura},
title = {Cross-lingual and multi-stream posterior features for low resource
{LVCSR} systems},
booktitle = {{INTERSPEECH} 2010, 11th Annual Conference of the International Speech
Communication Association, Makuhari, Chiba, Japan, September 26-30,
2010},
pages = {877--880},
publisher = {{ISCA}},
year = {2010},
url = {https://doi.org/10.21437/Interspeech.2010-295},
doi = {10.21437/INTERSPEECH.2010-295},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/ThomasGH10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/JansenCH10,
author = {Aren Jansen and
Kenneth Church and
Hynek Hermansky},
editor = {Takao Kobayashi and
Keikichi Hirose and
Satoshi Nakamura},
title = {Towards spoken term discovery at scale with zero resources},
booktitle = {{INTERSPEECH} 2010, 11th Annual Conference of the International Speech
Communication Association, Makuhari, Chiba, Japan, September 26-30,
2010},
pages = {1676--1679},
publisher = {{ISCA}},
year = {2010},
url = {https://doi.org/10.21437/Interspeech.2010-483},
doi = {10.21437/INTERSPEECH.2010-483},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/JansenCH10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/SivaramGH10,
author = {Garimella S. V. S. Sivaram and
Sriram Ganapathy and
Hynek Hermansky},
editor = {Takao Kobayashi and
Keikichi Hirose and
Satoshi Nakamura},
title = {Sparse auto-associative neural networks: theory and application to
speech recognition},
booktitle = {{INTERSPEECH} 2010, 11th Annual Conference of the International Speech
Communication Association, Makuhari, Chiba, Japan, September 26-30,
2010},
pages = {2270--2273},
publisher = {{ISCA}},
year = {2010},
url = {https://doi.org/10.21437/Interspeech.2010-623},
doi = {10.21437/INTERSPEECH.2010-623},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/SivaramGH10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/ThomasPGMH10,
author = {Samuel Thomas and
Kailash Patil and
Sriram Ganapathy and
Nima Mesgarani and
Hynek Hermansky},
editor = {Takao Kobayashi and
Keikichi Hirose and
Satoshi Nakamura},
title = {A phoneme recognition framework based on auditory spectro-temporal
receptive fields},
booktitle = {{INTERSPEECH} 2010, 11th Annual Conference of the International Speech
Communication Association, Makuhari, Chiba, Japan, September 26-30,
2010},
pages = {2458--2461},
publisher = {{ISCA}},
year = {2010},
url = {https://doi.org/10.21437/Interspeech.2010-661},
doi = {10.21437/INTERSPEECH.2010-661},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/ThomasPGMH10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iscas/LiuMHH10,
author = {Shih{-}Chii Liu and
Nima Mesgarani and
John G. Harris and
Hynek Hermansky},
title = {The use of spike-based representations for hardware audition systems},
booktitle = {International Symposium on Circuits and Systems {(ISCAS} 2010), May
30 - June 2, 2010, Paris, France},
pages = {505--508},
publisher = {{IEEE}},
year = {2010},
url = {https://doi.org/10.1109/ISCAS.2010.5537588},
doi = {10.1109/ISCAS.2010.5537588},
timestamp = {Wed, 16 Oct 2019 14:14:49 +0200},
biburl = {https://dblp.org/rec/conf/iscas/LiuMHH10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iscas/DelbruckKBH10,
author = {Tobi Delbr{\"{u}}ck and
Thomas Koch and
Raphael Berner and
Hynek Hermansky},
title = {Fully integrated 500uW speech detection wake-up circuit},
booktitle = {International Symposium on Circuits and Systems {(ISCAS} 2010), May
30 - June 2, 2010, Paris, France},
pages = {2015--2018},
publisher = {{IEEE}},
year = {2010},
url = {https://doi.org/10.1109/ISCAS.2010.5537160},
doi = {10.1109/ISCAS.2010.5537160},
timestamp = {Tue, 29 Dec 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/iscas/DelbruckKBH10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/tsd/KombrinkHBH10,
author = {Stefan Kombrink and
Mirko Hannemann and
Luk{\'{a}}s Burget and
Hynek Hermansky},
editor = {Petr Sojka and
Ales Hor{\'{a}}k and
Ivan Kopecek and
Karel Pala},
title = {Recovery of Rare Words in Lecture Speech},
booktitle = {Text, Speech and Dialogue, 13th International Conference, {TSD} 2010,
Brno, Czech Republic, September 6-10, 2010. Proceedings},
series = {Lecture Notes in Computer Science},
volume = {6231},
pages = {330--337},
publisher = {Springer},
year = {2010},
url = {https://doi.org/10.1007/978-3-642-15760-8\_42},
doi = {10.1007/978-3-642-15760-8\_42},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/tsd/KombrinkHBH10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/asru/GanapathyTH09,
author = {Sriram Ganapathy and
Samuel Thomas and
Hynek Hermansky},
title = {Temporal envelope subtraction for robust speech recognition using
modulation spectrum},
booktitle = {2009 {IEEE} Workshop on Automatic Speech Recognition {\&} Understanding,
{ASRU} 2009, Merano/Meran, Italy, December 13-17, 2009},
pages = {164--169},
publisher = {{IEEE}},
year = {2009},
url = {https://doi.org/10.1109/ASRU.2009.5372922},
doi = {10.1109/ASRU.2009.5372922},
timestamp = {Fri, 03 Jul 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/asru/GanapathyTH09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/PavelSH09,
author = {Misha Pavel and
Malcolm Slaney and
Hynek Hermansky},
title = {Reconciliation of human and machine speech recognition performance},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing, {ICASSP} 2009, 19-24 April 2009, Taipei, Taiwan},
pages = {1669--1672},
publisher = {{IEEE}},
year = {2009},
url = {https://doi.org/10.1109/ICASSP.2009.4959922},
doi = {10.1109/ICASSP.2009.4959922},
timestamp = {Thu, 23 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/PavelSH09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/PintoSHM09,
author = {Joel Pinto and
Garimella S. V. S. Sivaram and
Hynek Hermansky and
Mathew Magimai{-}Doss},
title = {Volterra series for analyzing {MLP} based phoneme posterior estimator},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing, {ICASSP} 2009, 19-24 April 2009, Taipei, Taiwan},
pages = {1813--1816},
publisher = {{IEEE}},
year = {2009},
url = {https://doi.org/10.1109/ICASSP.2009.4959958},
doi = {10.1109/ICASSP.2009.4959958},
timestamp = {Thu, 23 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/PintoSHM09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/ThomasGH09,
author = {Samuel Thomas and
Sriram Ganapathy and
Hynek Hermansky},
title = {Phoneme recognition using spectral envelope and modulation frequency
features},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing, {ICASSP} 2009, 19-24 April 2009, Taipei, Taiwan},
pages = {4453--4456},
publisher = {{IEEE}},
year = {2009},
url = {https://doi.org/10.1109/ICASSP.2009.4960618},
doi = {10.1109/ICASSP.2009.4960618},
timestamp = {Thu, 23 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/ThomasGH09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/KombrinkBMKH09,
author = {Stefan Kombrink and
Luk{\'{a}}s Burget and
Pavel Matejka and
Martin Karafi{\'{a}}t and
Hynek Hermansky},
title = {Posterior-based out of vocabulary word detection in telephone speech},
booktitle = {{INTERSPEECH} 2009, 10th Annual Conference of the International Speech
Communication Association, Brighton, United Kingdom, September 6-10,
2009},
pages = {80--83},
publisher = {{ISCA}},
year = {2009},
url = {https://doi.org/10.21437/Interspeech.2009-18},
doi = {10.21437/INTERSPEECH.2009-18},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/KombrinkBMKH09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/MotlicekGH09,
author = {Petr Motl{\'{\i}}cek and
Sriram Ganapathy and
Hynek Hermansky},
title = {Arithmetic coding of sub-band residuals in {FDLP} speech/audio codec},
booktitle = {{INTERSPEECH} 2009, 10th Annual Conference of the International Speech
Communication Association, Brighton, United Kingdom, September 6-10,
2009},
pages = {2591--2594},
publisher = {{ISCA}},
year = {2009},
url = {https://doi.org/10.21437/Interspeech.2009-682},
doi = {10.21437/INTERSPEECH.2009-682},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/MotlicekGH09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/GanapathyTH09,
author = {Sriram Ganapathy and
Samuel Thomas and
Hynek Hermansky},
title = {Static and dynamic modulation spectrum for speech recognition},
booktitle = {{INTERSPEECH} 2009, 10th Annual Conference of the International Speech
Communication Association, Brighton, United Kingdom, September 6-10,
2009},
pages = {2823--2826},
publisher = {{ISCA}},
year = {2009},
url = {https://doi.org/10.21437/Interspeech.2009-721},
doi = {10.21437/INTERSPEECH.2009-721},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/GanapathyTH09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/ThomasGH09,
author = {Samuel Thomas and
Sriram Ganapathy and
Hynek Hermansky},
title = {Tandem representations of spectral envelope and modulation frequency
features for {ASR}},
booktitle = {{INTERSPEECH} 2009, 10th Annual Conference of the International Speech
Communication Association, Brighton, United Kingdom, September 6-10,
2009},
pages = {2955--2958},
publisher = {{ISCA}},
year = {2009},
url = {https://doi.org/10.21437/Interspeech.2009-748},
doi = {10.21437/INTERSPEECH.2009-748},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/ThomasGH09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/MesgaraniSNEH09,
author = {Nima Mesgarani and
Garimella S. V. S. Sivaram and
Sridhar Krishna Nemala and
Mounya Elhilali and
Hynek Hermansky},
title = {Discriminant spectrotemporal features for phoneme recognition},
booktitle = {{INTERSPEECH} 2009, 10th Annual Conference of the International Speech
Communication Association, Brighton, United Kingdom, September 6-10,
2009},
pages = {2983--2986},
publisher = {{ISCA}},
year = {2009},
url = {https://doi.org/10.21437/Interspeech.2009-755},
doi = {10.21437/INTERSPEECH.2009-755},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/MesgaraniSNEH09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/tsd/GanapathyMH09,
author = {Sriram Ganapathy and
Petr Motl{\'{\i}}cek and
Hynek Hermansky},
editor = {V{\'{a}}clav Matousek and
Pavel Mautner},
title = {Error Resilient Speech Coding Using Sub-band Hilbert Envelopes},
booktitle = {Text, Speech and Dialogue, 12th International Conference, {TSD} 2009,
Pilsen, Czech Republic, September 13-17, 2009. Proceedings},
series = {Lecture Notes in Computer Science},
volume = {5729},
pages = {355--362},
publisher = {Springer},
year = {2009},
url = {https://doi.org/10.1007/978-3-642-04208-9\_49},
doi = {10.1007/978-3-642-04208-9\_49},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/tsd/GanapathyMH09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/waspaa/GanapathyTMH09,
author = {Sriram Ganapathy and
Samuel Thomas and
Petr Motl{\'{\i}}cek and
Hynek Hermansky},
title = {Applications of signal analysis using autoregressive models for amplitude
modulation},
booktitle = {{IEEE} Workshop on Applications of Signal Processing to Audio and
Acoustics, {WASPAA} '09, New Paltz, NY, USA, October 18-21, 2009},
pages = {341--344},
publisher = {{IEEE}},
year = {2009},
url = {https://doi.org/10.1109/ASPAA.2009.5346495},
doi = {10.1109/ASPAA.2009.5346495},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/waspaa/GanapathyTMH09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@incollection{DBLP:series/lncs/StrickerWABHPRT09,
author = {Claude Stricker and
Jean{-}Fr{\'{e}}d{\'{e}}ric Wagen and
Guillermo Aradilla and
Herv{\'{e}} Bourlard and
Hynek Hermansky and
Joel Pinto and
Paul{-}Henri Rey and
J{\'{e}}r{\^{o}}me Th{\'{e}}raulaz},
editor = {Denis Lalanne and
J{\"{u}}rg Kohlas},
title = {Intelligent Multi-modal Interfaces for Mobile Applications in Hostile
Environment(IM-HOST)},
booktitle = {Human Machine Interaction, Research Results of the {MMI} Program},
series = {Lecture Notes in Computer Science},
volume = {5440},
pages = {71--102},
publisher = {Springer},
year = {2009},
url = {https://doi.org/10.1007/978-3-642-00437-7\_4},
doi = {10.1007/978-3-642-00437-7\_4},
timestamp = {Tue, 14 May 2019 10:00:55 +0200},
biburl = {https://dblp.org/rec/series/lncs/StrickerWABHPRT09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/spl/ThomasGH08,
author = {Samuel Thomas and
Sriram Ganapathy and
Hynek Hermansky},
title = {Recognition of Reverberant Speech Using Frequency Domain Linear Prediction},
journal = {{IEEE} Signal Process. Lett.},
volume = {15},
pages = {681--684},
year = {2008},
url = {https://doi.org/10.1109/LSP.2008.2002708},
doi = {10.1109/LSP.2008.2002708},
timestamp = {Fri, 03 Jul 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/spl/ThomasGH08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/eusipco/SivaramH08,
author = {Garimella S. V. S. Sivaram and
Hynek Hermansky},
title = {Emulating temporal receptive fields of auditory mid-brain neurons
for automatic speech recognition},
booktitle = {2008 16th European Signal Processing Conference, {EUSIPCO} 2008, Lausanne,
Switzerland, August 25-29, 2008},
pages = {1--4},
publisher = {{IEEE}},
year = {2008},
url = {https://ieeexplore.ieee.org/document/7080488/},
timestamp = {Mon, 09 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/eusipco/SivaramH08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/eusipco/ThomasGH08,
author = {Samuel Thomas and
Sriram Ganapathy and
Hynek Hermansky},
title = {Spectro-temporal features for Automatic Speech Recognition using Linear
Prediction in spectral domain},
booktitle = {2008 16th European Signal Processing Conference, {EUSIPCO} 2008, Lausanne,
Switzerland, August 25-29, 2008},
pages = {1--4},
publisher = {{IEEE}},
year = {2008},
url = {https://ieeexplore.ieee.org/document/7080560/},
timestamp = {Mon, 09 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/eusipco/ThomasGH08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/eusipco/TosicMH08,
author = {Tamara Tosic and
Mathew Magimai{-}Doss and
Hynek Hermansky},
title = {Using comparison of parallel phoneme probability streams for {OOV}
word detection},
booktitle = {2008 16th European Signal Processing Conference, {EUSIPCO} 2008, Lausanne,
Switzerland, August 25-29, 2008},
pages = {1--5},
publisher = {{IEEE}},
year = {2008},
url = {https://ieeexplore.ieee.org/document/7080707/},
timestamp = {Mon, 09 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/eusipco/TosicMH08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/BurgetSMHRWKHC08,
author = {Luk{\'{a}}s Burget and
Petr Schwarz and
Pavel Matejka and
Mirko Hannemann and
Ariya Rastrow and
Christopher M. White and
Sanjeev Khudanpur and
Hynek Hermansky and
Jan Cernock{\'{y}}},
title = {Combination of strongly and weakly constrained recognizers for reliable
detection of {OOVS}},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing, {ICASSP} 2008, March 30 - April 4, 2008, Caesars
Palace, Las Vegas, Nevada, {USA}},
pages = {4081--4084},
publisher = {{IEEE}},
year = {2008},
url = {https://doi.org/10.1109/ICASSP.2008.4518551},
doi = {10.1109/ICASSP.2008.4518551},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/BurgetSMHRWKHC08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/WhiteZBSH08,
author = {Christopher M. White and
Geoffrey Zweig and
Luk{\'{a}}s Burget and
Petr Schwarz and
Hynek Hermansky},
title = {Confidence estimation, {OOV} detection and language {ID} using phone-to-word
transduction and phone-level alignments},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing, {ICASSP} 2008, March 30 - April 4, 2008, Caesars
Palace, Las Vegas, Nevada, {USA}},
pages = {4085--4088},
publisher = {{IEEE}},
year = {2008},
url = {https://doi.org/10.1109/ICASSP.2008.4518552},
doi = {10.1109/ICASSP.2008.4518552},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/WhiteZBSH08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/ValenteH08,
author = {Fabio Valente and
Hynek Hermansky},
title = {Hierarchical and parallel processing of modulation spectrum for {ASR}
applications},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing, {ICASSP} 2008, March 30 - April 4, 2008, Caesars
Palace, Las Vegas, Nevada, {USA}},
pages = {4165--4168},
publisher = {{IEEE}},
year = {2008},
url = {https://doi.org/10.1109/ICASSP.2008.4518572},
doi = {10.1109/ICASSP.2008.4518572},
timestamp = {Fri, 19 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/ValenteH08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/PintoYHM08,
author = {Joel Pinto and
B. Yegnanarayana and
Hynek Hermansky and
Mathew Magimai{-}Doss},
title = {Exploiting contextual information for improved phoneme recognition},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing, {ICASSP} 2008, March 30 - April 4, 2008, Caesars
Palace, Las Vegas, Nevada, {USA}},
pages = {4449--4452},
publisher = {{IEEE}},
year = {2008},
url = {https://doi.org/10.1109/ICASSP.2008.4518643},
doi = {10.1109/ICASSP.2008.4518643},
timestamp = {Fri, 21 May 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/PintoYHM08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/GanapathyMHG08,
author = {Sriram Ganapathy and
Petr Motl{\'{\i}}cek and
Hynek Hermansky and
Harinath Garudadri},
title = {Temporal masking for bit-rate reduction in audio codec based on Frequency
Domain Linear Prediction},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing, {ICASSP} 2008, March 30 - April 4, 2008, Caesars
Palace, Las Vegas, Nevada, {USA}},
pages = {4781--4784},
publisher = {{IEEE}},
year = {2008},
url = {https://doi.org/10.1109/ICASSP.2008.4518726},
doi = {10.1109/ICASSP.2008.4518726},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/GanapathyMHG08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icmi/AnemullerBCHJKLMPPTGZH08,
author = {J{\"{o}}rn Anem{\"{u}}ller and
J{\"{o}}rg{-}Hendrik Bach and
Barbara Caputo and
Michal Havlena and
Jie Luo and
Hendrik Kayser and
Bastian Leibe and
Petr Motl{\'{\i}}cek and
Tom{\'{a}}s Pajdla and
Misha Pavel and
Akihiko Torii and
Luc Van Gool and
Alon Zweig and
Hynek Hermansky},
editor = {Vassilios Digalakis and
Alexandros Potamianos and
Matthew A. Turk and
Roberto Pieraccini and
Yuri Ivanov},
title = {The {DIRAC} {AWEAR} audio-visual platform for detection of unexpected
and incongruent events},
booktitle = {Proceedings of the 10th International Conference on Multimodal Interfaces,
{ICMI} 2008, Chania, Crete, Greece, October 20-22, 2008},
pages = {289--292},
publisher = {{ACM}},
year = {2008},
url = {https://doi.org/10.1145/1452392.1452451},
doi = {10.1145/1452392.1452451},
timestamp = {Wed, 07 Dec 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icmi/AnemullerBCHJKLMPPTGZH08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/GanapathyMHG08,
author = {Sriram Ganapathy and
Petr Motl{\'{\i}}cek and
Hynek Hermansky and
Harinath Garudadri},
title = {Spectral noise shaping: improvements in speech/audio codec based on
linear prediction in spectral domain},
booktitle = {{INTERSPEECH} 2008, 9th Annual Conference of the International Speech
Communication Association, Brisbane, Australia, September 22-26, 2008},
pages = {675--678},
publisher = {{ISCA}},
year = {2008},
url = {https://doi.org/10.21437/Interspeech.2008-215},
doi = {10.21437/INTERSPEECH.2008-215},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/GanapathyMHG08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/SivaramH08,
author = {Garimella S. V. S. Sivaram and
Hynek Hermansky},
title = {Introducing temporal asymmetries in feature extraction for automatic
speech recognition},
booktitle = {{INTERSPEECH} 2008, 9th Annual Conference of the International Speech
Communication Association, Brisbane, Australia, September 22-26, 2008},
pages = {890--893},
publisher = {{ISCA}},
year = {2008},
url = {https://doi.org/10.21437/Interspeech.2008-207},
doi = {10.21437/INTERSPEECH.2008-207},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/SivaramH08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/GanapathyTH08,
author = {Sriram Ganapathy and
Samuel Thomas and
Hynek Hermansky},
title = {Front-end for far-field speech recognition based on frequency domain
linear prediction},
booktitle = {{INTERSPEECH} 2008, 9th Annual Conference of the International Speech
Communication Association, Brisbane, Australia, September 22-26, 2008},
pages = {984--987},
publisher = {{ISCA}},
year = {2008},
url = {https://doi.org/10.21437/Interspeech.2008-287},
doi = {10.21437/INTERSPEECH.2008-287},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/GanapathyTH08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/ThomasGH08,
author = {Samuel Thomas and
Sriram Ganapathy and
Hynek Hermansky},
title = {Hilbert envelope based spectro-temporal features for phoneme recognition
in telephone speech},
booktitle = {{INTERSPEECH} 2008, 9th Annual Conference of the International Speech
Communication Association, Brisbane, Australia, September 22-26, 2008},
pages = {1521--1524},
publisher = {{ISCA}},
year = {2008},
url = {https://doi.org/10.21437/Interspeech.2008-436},
doi = {10.21437/INTERSPEECH.2008-436},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/ThomasGH08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/ValenteH08,
author = {Fabio Valente and
Hynek Hermansky},
title = {On the combination of auditory and modulation frequency channels for
{ASR} applications},
booktitle = {{INTERSPEECH} 2008, 9th Annual Conference of the International Speech
Communication Association, Brisbane, Australia, September 22-26, 2008},
pages = {2242--2245},
publisher = {{ISCA}},
year = {2008},
url = {https://doi.org/10.21437/Interspeech.2008-445},
doi = {10.21437/INTERSPEECH.2008-445},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/ValenteH08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/PintoH08,
author = {Joel Pinto and
Hynek Hermansky},
title = {Combining evidence from a generative and a discriminative model in
phoneme recognition},
booktitle = {{INTERSPEECH} 2008, 9th Annual Conference of the International Speech
Communication Association, Brisbane, Australia, September 22-26, 2008},
pages = {2414--2417},
publisher = {{ISCA}},
year = {2008},
url = {https://doi.org/10.21437/Interspeech.2008-132},
doi = {10.21437/INTERSPEECH.2008-132},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/PintoH08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/mlmi/ThomasGH08,
author = {Samuel Thomas and
Sriram Ganapathy and
Hynek Hermansky},
editor = {Andrei Popescu{-}Belis and
Rainer Stiefelhagen},
title = {Hilbert Envelope Based Features for Far-Field Speech Recognition},
booktitle = {Machine Learning for Multimodal Interaction, 5th International Workshop,
{MLMI} 2008, Utrecht, The Netherlands, September 8-10, 2008. Proceedings},
series = {Lecture Notes in Computer Science},
volume = {5237},
pages = {119--124},
publisher = {Springer},
year = {2008},
url = {https://doi.org/10.1007/978-3-540-85853-9\_11},
doi = {10.1007/978-3-540-85853-9\_11},
timestamp = {Fri, 03 Jul 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/mlmi/ThomasGH08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/WeinshallHZLJOP08,
author = {Daphna Weinshall and
Hynek Hermansky and
Alon Zweig and
Jie Luo and
Holly Br{\"{u}}gge Jimison and
Frank W. Ohl and
Misha Pavel},
editor = {Daphne Koller and
Dale Schuurmans and
Yoshua Bengio and
L{\'{e}}on Bottou},
title = {Beyond Novelty Detection: Incongruent Events, when General and Specific
Classifiers Disagree},
booktitle = {Advances in Neural Information Processing Systems 21, Proceedings
of the Twenty-Second Annual Conference on Neural Information Processing
Systems, Vancouver, British Columbia, Canada, December 8-11, 2008},
pages = {1745--1752},
publisher = {Curran Associates, Inc.},
year = {2008},
url = {https://proceedings.neurips.cc/paper/2008/hash/6c9882bbac1c7093bd25041881277658-Abstract.html},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/WeinshallHZLJOP08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/tsd/MotlicekGHGA08,
author = {Petr Motl{\'{\i}}cek and
Sriram Ganapathy and
Hynek Hermansky and
Harinath Garudadri and
Marios Athineos},
editor = {Petr Sojka and
Ales Hor{\'{a}}k and
Ivan Kopecek and
Karel Pala},
title = {Perceptually Motivated Sub-band Decomposition for {FDLP} Audio Coding},
booktitle = {Text, Speech and Dialogue, 11th International Conference, {TSD} 2008,
Brno, Czech Republic, September 8-12, 2008. Proceedings},
series = {Lecture Notes in Computer Science},
volume = {5246},
pages = {435--442},
publisher = {Springer},
year = {2008},
url = {https://doi.org/10.1007/978-3-540-87391-4\_56},
doi = {10.1007/978-3-540-87391-4\_56},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/tsd/MotlicekGHGA08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/tsd/ParthasarathiMH08,
author = {Sree Hari Krishnan Parthasarathi and
Petr Motl{\'{\i}}cek and
Hynek Hermansky},
editor = {Petr Sojka and
Ales Hor{\'{a}}k and
Ivan Kopecek and
Karel Pala},
title = {Exploiting Contextual Information for Speech/Non-Speech Detection},
booktitle = {Text, Speech and Dialogue, 11th International Conference, {TSD} 2008,
Brno, Czech Republic, September 8-12, 2008. Proceedings},
series = {Lecture Notes in Computer Science},
volume = {5246},
pages = {451--459},
publisher = {Springer},
year = {2008},
url = {https://doi.org/10.1007/978-3-540-87391-4\_58},
doi = {10.1007/978-3-540-87391-4\_58},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/tsd/ParthasarathiMH08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/tsd/PintoSH08,
author = {Joel Pinto and
Garimella S. V. S. Sivaram and
Hynek Hermansky},
editor = {Petr Sojka and
Ales Hor{\'{a}}k and
Ivan Kopecek and
Karel Pala},
title = {Reverse Correlation for Analyzing {MLP} Posterior Features in {ASR}},
booktitle = {Text, Speech and Dialogue, 11th International Conference, {TSD} 2008,
Brno, Czech Republic, September 8-12, 2008. Proceedings},
series = {Lecture Notes in Computer Science},
volume = {5246},
pages = {469--476},
publisher = {Springer},
year = {2008},
url = {https://doi.org/10.1007/978-3-540-87391-4\_60},
doi = {10.1007/978-3-540-87391-4\_60},
timestamp = {Thu, 25 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/tsd/PintoSH08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/tsd/SivaramH08,
author = {Garimella S. V. S. Sivaram and
Hynek Hermansky},
editor = {Petr Sojka and
Ales Hor{\'{a}}k and
Ivan Kopecek and
Karel Pala},
title = {Emulating Temporal Receptive Fields of Higher Level Auditory Neurons
for {ASR}},
booktitle = {Text, Speech and Dialogue, 11th International Conference, {TSD} 2008,
Brno, Czech Republic, September 8-12, 2008. Proceedings},
series = {Lecture Notes in Computer Science},
volume = {5246},
pages = {509--516},
publisher = {Springer},
year = {2008},
url = {https://doi.org/10.1007/978-3-540-87391-4\_65},
doi = {10.1007/978-3-540-87391-4\_65},
timestamp = {Thu, 25 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/tsd/SivaramH08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/MotlicekUH07,
author = {Petr Motl{\'{\i}}cek and
Vijay Ullal and
Hynek Hermansky},
title = {Wide-Band Perceptual Audio Coding Based on Frequency-Domain Linear
Prediction},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing, {ICASSP} 2007, Honolulu, Hawaii, USA, April
15-20, 2007},
pages = {265--268},
publisher = {{IEEE}},
year = {2007},
url = {https://doi.org/10.1109/ICASSP.2007.366667},
doi = {10.1109/ICASSP.2007.366667},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/MotlicekUH07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/ValenteH07,
author = {Fabio Valente and
Hynek Hermansky},
title = {Combination of Acoustic Classifiers Based on Dempster-Shafer Theory
of Evidence},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing, {ICASSP} 2007, Honolulu, Hawaii, USA, April
15-20, 2007},
pages = {1129--1132},
publisher = {{IEEE}},
year = {2007},
url = {https://doi.org/10.1109/ICASSP.2007.367273},
doi = {10.1109/ICASSP.2007.367273},
timestamp = {Mon, 22 Jun 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/ValenteH07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/ValenteVPGHS07,
author = {Fabio Valente and
Jithendra Vepa and
Christian Plahl and
Christian Gollan and
Hynek Hermansky and
Ralf Schl{\"{u}}ter},
title = {Hierarchical neural networks feature extraction for {LVCSR} system},
booktitle = {{INTERSPEECH} 2007, 8th Annual Conference of the International Speech
Communication Association, Antwerp, Belgium, August 27-31, 2007},
pages = {42--45},
publisher = {{ISCA}},
year = {2007},
url = {https://doi.org/10.21437/Interspeech.2007-8},
doi = {10.21437/INTERSPEECH.2007-8},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/ValenteVPGHS07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/ValenteVH07,
author = {Fabio Valente and
Jithendra Vepa and
Hynek Hermansky},
title = {Multi-stream features combination based on dempster-shafer rule for
{LVCSR} system},
booktitle = {{INTERSPEECH} 2007, 8th Annual Conference of the International Speech
Communication Association, Antwerp, Belgium, August 27-31, 2007},
pages = {1154--1157},
publisher = {{ISCA}},
year = {2007},
url = {https://doi.org/10.21437/Interspeech.2007-375},
doi = {10.21437/INTERSPEECH.2007-375},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/ValenteVH07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/PrasannaH07,
author = {S. R. Mahadeva Prasanna and
Hynek Hermansky},
title = {{MRASTA} and {PLP} in automatic speech recognition},
booktitle = {{INTERSPEECH} 2007, 8th Annual Conference of the International Speech
Communication Association, Antwerp, Belgium, August 27-31, 2007},
pages = {1166--1169},
publisher = {{ISCA}},
year = {2007},
url = {https://doi.org/10.21437/Interspeech.2007-378},
doi = {10.21437/INTERSPEECH.2007-378},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/PrasannaH07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/KetabdarHH07,
author = {Hamed Ketabdar and
Mirko Hannemann and
Hynek Hermansky},
title = {Detection of out-of-vocabulary words in posterior based {ASR}},
booktitle = {{INTERSPEECH} 2007, 8th Annual Conference of the International Speech
Communication Association, Antwerp, Belgium, August 27-31, 2007},
pages = {1757--1760},
publisher = {{ISCA}},
year = {2007},
url = {https://doi.org/10.21437/Interspeech.2007-492},
doi = {10.21437/INTERSPEECH.2007-492},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/KetabdarHH07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/PintoLH07,
author = {Joel Pinto and
Andrew Lovitt and
Hynek Hermansky},
title = {Exploiting phoneme similarities in hybrid {HMM-ANN} keyword spotting},
booktitle = {{INTERSPEECH} 2007, 8th Annual Conference of the International Speech
Communication Association, Antwerp, Belgium, August 27-31, 2007},
pages = {1817--1820},
publisher = {{ISCA}},
year = {2007},
url = {https://doi.org/10.21437/Interspeech.2007-507},
doi = {10.21437/INTERSPEECH.2007-507},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/PintoLH07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/mlmi/MotlicekGHG07,
author = {Petr Motl{\'{\i}}cek and
Sriram Ganapathy and
Hynek Hermansky and
Harinath Garudadri},
editor = {Andrei Popescu{-}Belis and
Steve Renals and
Herv{\'{e}} Bourlard},
title = {Frequency Domain Linear Prediction for {QMF} Sub-bands and Applications
to Audio Coding},
booktitle = {Machine Learning for Multimodal Interaction , 4th International Workshop,
{MLMI} 2007, Brno, Czech Republic, June 28-30, 2007, Revised Selected
Papers},
series = {Lecture Notes in Computer Science},
volume = {4892},
pages = {248--258},
publisher = {Springer},
year = {2007},
url = {https://doi.org/10.1007/978-3-540-78155-4\_22},
doi = {10.1007/978-3-540-78155-4\_22},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/mlmi/MotlicekGHG07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/tsd/MotlicekHGG07,
author = {Petr Motl{\'{\i}}cek and
Hynek Hermansky and
Sriram Ganapathy and
Harinath Garudadri},
editor = {V{\'{a}}clav Matousek and
Pavel Mautner},
title = {Non-uniform Speech/Audio Coding Exploiting Predictability of Temporal
Evolution of Spectral Envelopes},
booktitle = {Text, Speech and Dialogue, 10th International Conference, {TSD} 2007,
Pilsen, Czech Republic, September 3-7, 2007, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {4629},
pages = {350--357},
publisher = {Springer},
year = {2007},
url = {https://doi.org/10.1007/978-3-540-74628-7\_46},
doi = {10.1007/978-3-540-74628-7\_46},
timestamp = {Tue, 14 May 2019 10:00:45 +0200},
biburl = {https://dblp.org/rec/conf/tsd/MotlicekHGG07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/FousekH06,
author = {Petr Fousek and
Hynek Hermansky},
title = {Towards {ASR} Based on Hierarchical Posterior-Based Keyword Recognition},
booktitle = {2006 {IEEE} International Conference on Acoustics Speech and Signal
Processing, {ICASSP} 2006, Toulouse, France, May 14-19, 2006},
pages = {433--436},
publisher = {{IEEE}},
year = {2006},
url = {https://doi.org/10.1109/ICASSP.2006.1660050},
doi = {10.1109/ICASSP.2006.1660050},
timestamp = {Mon, 22 Jun 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/FousekH06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/ValenteH06,
author = {Fabio Valente and
Hynek Hermansky},
title = {Discriminant linear processing of time-frequency plane},
booktitle = {{INTERSPEECH} 2006 - ICSLP, Ninth International Conference on Spoken
Language Processing, Pittsburgh, PA, USA, September 17-21, 2006},
publisher = {{ISCA}},
year = {2006},
url = {https://doi.org/10.21437/Interspeech.2006-119},
doi = {10.21437/INTERSPEECH.2006-119},
timestamp = {Thu, 22 Jun 2023 16:42:16 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/ValenteH06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/tsd/MotlicekHGS06,
author = {Petr Motl{\'{\i}}cek and
Hynek Hermansky and
Harinath Garudadri and
Naveen Srinivasamurthy},
editor = {Petr Sojka and
Ivan Kopecek and
Karel Pala},
title = {Speech Coding Based on Spectral Dynamics},
booktitle = {Text, Speech and Dialogue, 9th International Conference, {TSD} 2006,
Brno, Czech Republic, September 11-15, 2006, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {4188},
pages = {471--478},
publisher = {Springer},
year = {2006},
url = {https://doi.org/10.1007/11846406\_59},
doi = {10.1007/11846406\_59},
timestamp = {Tue, 14 May 2019 10:00:45 +0200},
biburl = {https://dblp.org/rec/conf/tsd/MotlicekHGS06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ejasp/VerhelstHKHJ05,
author = {Werner Verhelst and
J{\"{u}}rgen Herre and
Gernot Kubin and
Hynek Hermansky and
S{\o}ren Holdt Jensen},
title = {Editorial},
journal = {{EURASIP} J. Adv. Signal Process.},
volume = {2005},
number = {9},
pages = {1289--1291},
year = {2005},
url = {https://doi.org/10.1155/ASP.2005.1289},
doi = {10.1155/ASP.2005.1289},
timestamp = {Thu, 12 Mar 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/ejasp/VerhelstHKHJ05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/spm/MorganZSSSSOJHE05,
author = {Nelson Morgan and
Qifeng Zhu and
Andreas Stolcke and
M. Kemal S{\"{o}}nmez and
Sunil Sivadas and
Takahiro Shinozaki and
Mari Ostendorf and
Pratibha Jain and
Hynek Hermansky and
Dan Ellis and
George R. Doddington and
Barry Y. Chen and
{\"{O}}zg{\"{u}}r {\c{C}}etin and
Herv{\'{e}} Bourlard and
Marios Athineos},
title = {Pushing the envelope - aside [speech recognition]},
journal = {{IEEE} Signal Process. Mag.},
volume = {22},
number = {5},
pages = {81--88},
year = {2005},
url = {https://doi.org/10.1109/MSP.2005.1511826},
doi = {10.1109/MSP.2005.1511826},
timestamp = {Tue, 01 Jun 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/spm/MorganZSSSSOJHE05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/HermanskyF05,
author = {Hynek Hermansky and
Petr Fousek},
title = {Multi-resolution {RASTA} filtering for TANDEM-based {ASR}},
booktitle = {{INTERSPEECH} 2005 - Eurospeech, 9th European Conference on Speech
Communication and Technology, Lisbon, Portugal, September 4-8, 2005},
pages = {361--364},
publisher = {{ISCA}},
year = {2005},
url = {https://doi.org/10.21437/Interspeech.2005-184},
doi = {10.21437/INTERSPEECH.2005-184},
timestamp = {Thu, 22 Jun 2023 16:42:16 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/HermanskyF05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/tsd/HermanskyFL05,
author = {Hynek Hermansky and
Petr Fousek and
Mikko Lehtonen},
editor = {V{\'{a}}clav Matousek and
Pavel Mautner and
Tom{\'{a}}s Pavelka},
title = {The Role of Speech in Multimodal Human-Computer Interaction},
booktitle = {Text, Speech and Dialogue, 8th International Conference, {TSD} 2005,
Karlovy Vary, Czech Republic, September 12-15, 2005, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {3658},
pages = {2--8},
publisher = {Springer},
year = {2005},
url = {https://doi.org/10.1007/11551874\_2},
doi = {10.1007/11551874\_2},
timestamp = {Tue, 14 May 2019 10:00:45 +0200},
biburl = {https://dblp.org/rec/conf/tsd/HermanskyFL05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/MisraIBH04,
author = {Hemant Misra and
Shajith Ikbal and
Herv{\'{e}} Bourlard and
Hynek Hermansky},
title = {Spectral entropy based feature for robust {ASR}},
booktitle = {2004 {IEEE} International Conference on Acoustics, Speech, and Signal
Processing, {ICASSP} 2004, Montreal, Quebec, Canada, May 17-21, 2004},
pages = {193--196},
publisher = {{IEEE}},
year = {2004},
url = {https://doi.org/10.1109/ICASSP.2004.1325955},
doi = {10.1109/ICASSP.2004.1325955},
timestamp = {Sat, 30 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/MisraIBH04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/IkbalMBH04,
author = {Shajith Ikbal and
Hemant Misra and
Herv{\'{e}} Bourlard and
Hynek Hermansky},
title = {Phase autocorrelation {(PAC)} features in entropy based multi-stream
for robust speech recognition},
booktitle = {2004 {IEEE} International Conference on Acoustics, Speech, and Signal
Processing, {ICASSP} 2004, Montreal, Quebec, Canada, May 17-21, 2004},
pages = {205--208},
publisher = {{IEEE}},
year = {2004},
url = {https://doi.org/10.1109/ICASSP.2004.1325958},
doi = {10.1109/ICASSP.2004.1325958},
timestamp = {Sat, 30 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/IkbalMBH04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/SivadasH04,
author = {Sunil Sivadas and
Hynek Hermansky},
title = {On use of task independent training data in tandem feature extraction},
booktitle = {2004 {IEEE} International Conference on Acoustics, Speech, and Signal
Processing, {ICASSP} 2004, Montreal, Quebec, Canada, May 17-21, 2004},
pages = {541--544},
publisher = {{IEEE}},
year = {2004},
url = {https://doi.org/10.1109/ICASSP.2004.1326042},
doi = {10.1109/ICASSP.2004.1326042},
timestamp = {Mon, 22 Jun 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/SivadasH04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/AthineosHE04a,
author = {Marios Athineos and
Hynek Hermansky and
Daniel P. W. Ellis},
title = {PLP-squared: autoregressive modeling of auditory-like 2-d spectro-temporal
patterns},
booktitle = {{ISCA} Tutorial and Research Workshop on Statistical and Perceptual
Audio Processing, ICC, Jeju, Korea, October 3, 2004},
pages = {129},
publisher = {{ISCA}},
year = {2004},
url = {https://www.isca-speech.org/archive\_open/sapa\_04/sap4\_129.html},
timestamp = {Tue, 11 Jul 2023 11:45:03 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/AthineosHE04a.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/Hermansky04,
author = {Hynek Hermansky},
title = {Stochastic techniques in deriving perceptual knowledge},
booktitle = {{ISCA} Tutorial and Research Workshop on Statistical and Perceptual
Audio Processing, ICC, Jeju, Korea, October 3, 2004},
pages = {136},
publisher = {{ISCA}},
year = {2004},
url = {https://www.isca-speech.org/archive\_open/sapa\_04/sap4\_136.html},
timestamp = {Tue, 11 Jul 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/Hermansky04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/AthineosHE04,
author = {Marios Athineos and
Hynek Hermansky and
Daniel P. W. Ellis},
title = {{LP-TRAP:} linear predictive temporal patterns},
booktitle = {{INTERSPEECH} 2004 - ICSLP, 8th International Conference on Spoken
Language Processing, Jeju Island, Korea, October 4-8, 2004},
pages = {949--952},
publisher = {{ISCA}},
year = {2004},
url = {https://doi.org/10.21437/Interspeech.2004-344},
doi = {10.21437/INTERSPEECH.2004-344},
timestamp = {Thu, 22 Jun 2023 16:42:17 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/AthineosHE04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/IkbalMSHB04,
author = {Shajith Ikbal and
Hemant Misra and
Sunil Sivadas and
Hynek Hermansky and
Herv{\'{e}} Bourlard},
title = {Entropy based combination of tandem representations for noise robust
{ASR}},
booktitle = {{INTERSPEECH} 2004 - ICSLP, 8th International Conference on Spoken
Language Processing, Jeju Island, Korea, October 4-8, 2004},
pages = {2553--2556},
publisher = {{ISCA}},
year = {2004},
url = {https://doi.org/10.21437/Interspeech.2004-692},
doi = {10.21437/INTERSPEECH.2004-692},
timestamp = {Sat, 30 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/IkbalMSHB04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/FousekGHS04,
author = {Petr Fousek and
Frantisek Gr{\'{e}}zl and
Hynek Hermansky and
Petr Svojanovsky},
title = {New nonsense syllables database - analyses and preliminary {ASR} experiments},
booktitle = {{INTERSPEECH} 2004 - ICSLP, 8th International Conference on Spoken
Language Processing, Jeju Island, Korea, October 4-8, 2004},
pages = {2749--2752},
publisher = {{ISCA}},
year = {2004},
url = {https://doi.org/10.21437/Interspeech.2004-664},
doi = {10.21437/INTERSPEECH.2004-664},
timestamp = {Thu, 22 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/FousekGHS04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/speech/MalayathH03,
author = {Naren Malayath and
Hynek Hermansky},
title = {Data-driven spectral basis functions for automatic speech recognition},
journal = {Speech Commun.},
volume = {40},
number = {4},
pages = {449--466},
year = {2003},
url = {https://doi.org/10.1016/S0167-6393(02)00127-9},
doi = {10.1016/S0167-6393(02)00127-9},
timestamp = {Sat, 22 Feb 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/speech/MalayathH03.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/SivadasH03,
author = {Sunil Sivadas and
Hynek Hermansky},
title = {Generalized tandem feature extraction},
booktitle = {2003 {IEEE} International Conference on Acoustics, Speech, and Signal
Processing, {ICASSP} '03, Hong Kong, April 6-10, 2003},
pages = {56--59},
publisher = {{IEEE}},
year = {2003},
url = {https://doi.org/10.1109/ICASSP.2003.1198715},
doi = {10.1109/ICASSP.2003.1198715},
timestamp = {Mon, 22 Jun 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/SivadasH03.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/JainH03,
author = {Pratibha Jain and
Hynek Hermansky},
title = {Beyond a single critical-band in {TRAP} based {ASR}},
booktitle = {8th European Conference on Speech Communication and Technology, {EUROSPEECH}
2003 - {INTERSPEECH} 2003, Geneva, Switzerland, September 1-4, 2003},
pages = {437--440},
publisher = {{ISCA}},
year = {2003},
url = {https://doi.org/10.21437/Eurospeech.2003-164},
doi = {10.21437/EUROSPEECH.2003-164},
timestamp = {Thu, 22 Jun 2023 16:42:17 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/JainH03.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/SivadasH03,
author = {Sunil Sivadas and
Hynek Hermansky},
title = {In search of target class definition in tandem feature extraction},
booktitle = {8th European Conference on Speech Communication and Technology, {EUROSPEECH}
2003 - {INTERSPEECH} 2003, Geneva, Switzerland, September 1-4, 2003},
pages = {837--840},
publisher = {{ISCA}},
year = {2003},
url = {https://doi.org/10.21437/Eurospeech.2003-188},
doi = {10.21437/EUROSPEECH.2003-188},
timestamp = {Thu, 22 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/SivadasH03.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/AdamiH03,
author = {Andr{\'{e}} Gustavo Adami and
Hynek Hermansky},
title = {Segmentation of speech for speaker and language recognition},
booktitle = {8th European Conference on Speech Communication and Technology, {EUROSPEECH}
2003 - {INTERSPEECH} 2003, Geneva, Switzerland, September 1-4, 2003},
pages = {841--844},
publisher = {{ISCA}},
year = {2003},
url = {https://doi.org/10.21437/Eurospeech.2003-189},
doi = {10.21437/EUROSPEECH.2003-189},
timestamp = {Thu, 22 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/AdamiH03.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/HermanskyJ03,
author = {Hynek Hermansky and
Pratibha Jain},
title = {Band-independent speech-event categories for {TRAP} based {ASR}},
booktitle = {8th European Conference on Speech Communication and Technology, {EUROSPEECH}
2003 - {INTERSPEECH} 2003, Geneva, Switzerland, September 1-4, 2003},
pages = {1013--1016},
publisher = {{ISCA}},
year = {2003},
url = {https://doi.org/10.21437/Eurospeech.2003-201},
doi = {10.21437/EUROSPEECH.2003-201},
timestamp = {Thu, 22 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/HermanskyJ03.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/GrezlH03,
author = {Frantisek Gr{\'{e}}zl and
Hynek Hermansky},
title = {Local averaging and differentiating of spectral plane for TRAP-based
{ASR}},
booktitle = {8th European Conference on Speech Communication and Technology, {EUROSPEECH}
2003 - {INTERSPEECH} 2003, Geneva, Switzerland, September 1-4, 2003},
pages = {1017--1020},
publisher = {{ISCA}},
year = {2003},
url = {https://doi.org/10.21437/Eurospeech.2003-202},
doi = {10.21437/EUROSPEECH.2003-202},
timestamp = {Thu, 22 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/GrezlH03.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/KajarekarAH03,
author = {Sachin S. Kajarekar and
Andr{\'{e}} Gustavo Adami and
Hynek Hermansky},
title = {Novel approaches for one- and two-speaker detection},
booktitle = {8th European Conference on Speech Communication and Technology, {EUROSPEECH}
2003 - {INTERSPEECH} 2003, Geneva, Switzerland, September 1-4, 2003},
pages = {2661--2664},
publisher = {{ISCA}},
year = {2003},
url = {https://doi.org/10.21437/Eurospeech.2003-726},
doi = {10.21437/EUROSPEECH.2003-726},
timestamp = {Thu, 22 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/KajarekarAH03.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/tsd/MatejkaSHC03,
author = {Pavel Matejka and
Petr Schwarz and
Hynek Hermansky and
Jan Cernock{\'{y}}},
editor = {V{\'{a}}clav Matousek and
Pavel Mautner},
title = {Phoneme Recognition Using Temporal Patterns},
booktitle = {Text, Speech and Dialogue, 6th International Conference, {TSD} 2003,
Cesk{\'{e}} Budejovice, Czech Republic, September 8-12, 2003,
Proceedings},
series = {Lecture Notes in Computer Science},
volume = {2807},
pages = {198--205},
publisher = {Springer},
year = {2003},
url = {https://doi.org/10.1007/978-3-540-39398-6\_28},
doi = {10.1007/978-3-540-39398-6\_28},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/tsd/MatejkaSHC03.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/SivadasH02,
author = {Sunil Sivadas and
Hynek Hermansky},
title = {Hierarchical tandem feature extraction},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing, {ICASSP} 2002, May 13-17 2002, Orlando, Florida,
{USA}},
pages = {809--812},
publisher = {{IEEE}},
year = {2002},
url = {https://doi.org/10.1109/ICASSP.2002.5743841},
doi = {10.1109/ICASSP.2002.5743841},
timestamp = {Wed, 16 Oct 2019 14:14:52 +0200},
biburl = {https://dblp.org/rec/conf/icassp/SivadasH02.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/AdamKH02,
author = {Andr{\'{e}} Gustavo Adami and
Sachin S. Kajarekar and
Hynek Hermansky},
title = {A new speaker change detection method for two-speaker segmentation},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing, {ICASSP} 2002, May 13-17 2002, Orlando, Florida,
{USA}},
pages = {3908--3911},
publisher = {{IEEE}},
year = {2002},
url = {https://doi.org/10.1109/ICASSP.2002.5745511},
doi = {10.1109/ICASSP.2002.5745511},
timestamp = {Fri, 09 Dec 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/AdamKH02.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/AdamiBDGGHJKMS02,
author = {Andr{\'{e}} Gustavo Adami and
Luk{\'{a}}s Burget and
St{\'{e}}phane Dupont and
Harinath Garudadri and
Frantisek Gr{\'{e}}zl and
Hynek Hermansky and
Pratibha Jain and
Sachin S. Kajarekar and
Nelson Morgan and
Sunil Sivadas},
editor = {John H. L. Hansen and
Bryan L. Pellom},
title = {Qualcomm-ICSI-OGI features for {ASR}},
booktitle = {7th International Conference on Spoken Language Processing, {ICSLP2002}
- {INTERSPEECH} 2002, Denver, Colorado, USA, September 16-20, 2002},
pages = {21--24},
publisher = {{ISCA}},
year = {2002},
url = {https://doi.org/10.21437/ICSLP.2002-4},
doi = {10.21437/ICSLP.2002-4},
timestamp = {Mon, 26 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/AdamiBDGGHJKMS02.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/JainHK02,
author = {Pratibha Jain and
Hynek Hermansky and
Brian Kingsbury},
editor = {John H. L. Hansen and
Bryan L. Pellom},
title = {Distributed speech recognition using noise-robust {MFCC} and traps-estimated
manner features},
booktitle = {7th International Conference on Spoken Language Processing, {ICSLP2002}
- {INTERSPEECH} 2002, Denver, Colorado, USA, September 16-20, 2002},
pages = {473--476},
publisher = {{ISCA}},
year = {2002},
url = {https://doi.org/10.21437/ICSLP.2002-22},
doi = {10.21437/ICSLP.2002-22},
timestamp = {Thu, 22 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/JainHK02.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/MalayathH02,
author = {Naren Malayath and
Hynek Hermansky},
editor = {John H. L. Hansen and
Bryan L. Pellom},
title = {Bark resolution from speech data},
booktitle = {7th International Conference on Spoken Language Processing, {ICSLP2002}
- {INTERSPEECH} 2002, Denver, Colorado, USA, September 16-20, 2002},
pages = {2169--2172},
publisher = {{ISCA}},
year = {2002},
url = {https://doi.org/10.21437/ICSLP.2002-592},
doi = {10.21437/ICSLP.2002-592},
timestamp = {Thu, 22 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/MalayathH02.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/KajarekarH02,
author = {Sachin S. Kajarekar and
Hynek Hermansky},
editor = {Suzanna Becker and
Sebastian Thrun and
Klaus Obermayer},
title = {Analysis of Information in Speech Based on {MANOVA}},
booktitle = {Advances in Neural Information Processing Systems 15 [Neural Information
Processing Systems, {NIPS} 2002, December 9-14, 2002, Vancouver, British
Columbia, Canada]},
pages = {1189--1196},
publisher = {{MIT} Press},
year = {2002},
url = {https://proceedings.neurips.cc/paper/2002/hash/333ac5d90817d69113471fbb6e531bee-Abstract.html},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/KajarekarH02.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/KajarekarYH01,
author = {Sachin S. Kajarekar and
Bayya Yegnanarayana and
Hynek Hermansky},
title = {A study of two dimensional linear discriminants for {ASR}},
booktitle = {{IEEE} International Conference on Acoustics, Speech, and Signal Processing,
{ICASSP} 2001, 7-11 May, 2001, Salt Palace Convention Center, Salt
Lake City, Utah, USA, Proceedings},
pages = {137--140},
publisher = {{IEEE}},
year = {2001},
url = {https://doi.org/10.1109/ICASSP.2001.940786},
doi = {10.1109/ICASSP.2001.940786},
timestamp = {Thu, 23 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/KajarekarYH01.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/BenitezBCDGHJKMS01,
author = {M. Carmen Ben{\'{\i}}tez and
Luk{\'{a}}s Burget and
Barry Y. Chen and
St{\'{e}}phane Dupont and
Harinath Garudadri and
Hynek Hermansky and
Pratibha Jain and
Sachin S. Kajarekar and
Nelson Morgan and
Sunil Sivadas},
editor = {Paul Dalsgaard and
B{\o}rge Lindberg and
Henrik Benner and
Zheng{-}Hua Tan},
title = {Robust {ASR} front-end using spectral-based and discriminant features:
experiments on the Aurora tasks},
booktitle = {{EUROSPEECH} 2001 Scandinavia, 7th European Conference on Speech Communication
and Technology, 2nd {INTERSPEECH} Event, Aalborg, Denmark, September
3-7, 2001},
pages = {429--432},
publisher = {{ISCA}},
year = {2001},
url = {https://doi.org/10.21437/Eurospeech.2001-115},
doi = {10.21437/EUROSPEECH.2001-115},
timestamp = {Thu, 22 Jun 2023 16:42:18 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/BenitezBCDGHJKMS01.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/odyssey/KajarekarH01,
author = {Sachin S. Kajarekar and
Hynek Hermansky},
title = {Speaker verification based on broad phonetic categories},
booktitle = {2001: {A} Speaker Odyssey - The Speaker Recognition Workshop, Crete,
Greece, June 18-22, 2001},
pages = {201--206},
publisher = {{ISCA}},
year = {2001},
url = {http://www.isca-speech.org/archive\_open/odyssey/odys\_201.html},
timestamp = {Wed, 10 Feb 2021 08:42:15 +0100},
biburl = {https://dblp.org/rec/conf/odyssey/KajarekarH01.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/tsd/Hermansky01,
author = {Hynek Hermansky},
editor = {V{\'{a}}clav Matousek and
Pavel Mautner and
Roman Moucek and
Karel Tauser},
title = {Human Speech Perception: Some Lessons from Automatic Speech Recognition},
booktitle = {Text, Speech and Dialogue, 4th International Conference, {TSD} 2001,
Zelezna Ruda, Czech Republic, September 11-13, 2001, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {2166},
pages = {187--196},
publisher = {Springer},
year = {2001},
url = {https://doi.org/10.1007/3-540-44805-5\_24},
doi = {10.1007/3-540-44805-5\_24},
timestamp = {Tue, 14 May 2019 10:00:45 +0200},
biburl = {https://dblp.org/rec/conf/tsd/Hermansky01.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/tsd/BurgetH01,
author = {Luk{\'{a}}s Burget and
Hynek Hermansky},
editor = {V{\'{a}}clav Matousek and
Pavel Mautner and
Roman Moucek and
Karel Tauser},
title = {Data Driven Design of Filter Bank for Speech Recognition},
booktitle = {Text, Speech and Dialogue, 4th International Conference, {TSD} 2001,
Zelezna Ruda, Czech Republic, September 11-13, 2001, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {2166},
pages = {299--304},
publisher = {Springer},
year = {2001},
url = {https://doi.org/10.1007/3-540-44805-5\_40},
doi = {10.1007/3-540-44805-5\_40},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/tsd/BurgetH01.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/dsp/MalayathHKY00,
author = {Naren Malayath and
Hynek Hermansky and
Sachin S. Kajarekar and
B. Yegnanarayana},
title = {Data-Driven Temporal Filters and Alternatives to {GMM} in Speaker
Verification},
journal = {Digit. Signal Process.},
volume = {10},
number = {1-3},
pages = {55--74},
year = {2000},
url = {https://doi.org/10.1006/dspr.1999.0363},
doi = {10.1006/DSPR.1999.0363},
timestamp = {Fri, 21 May 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/dsp/MalayathHKY00.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/speech/YangVSH00,
author = {Howard Hua Yang and
Sarel van Vuuren and
Sangita Sharma and
Hynek Hermansky},
title = {Relevance of time-frequency features for phonetic and speaker-channel
classification},
journal = {Speech Commun.},
volume = {31},
number = {1},
pages = {35--50},
year = {2000},
url = {https://doi.org/10.1016/S0167-6393(00)00007-8},
doi = {10.1016/S0167-6393(00)00007-8},
timestamp = {Sat, 22 Feb 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/speech/YangVSH00.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/SharmaEKJH00,
author = {Sangita Sharma and
Dan Ellis and
Sachin S. Kajarekar and
Pratibha Jain and
Hynek Hermansky},
title = {Feature extraction using non-linear transformation for robust speech
recognition on the Aurora database},
booktitle = {{IEEE} International Conference on Acoustics, Speech, and Signal Processing.
{ICASSP} 2000, 5-9 June, 2000, Hilton Hotel and Convention Center,
Istanbul, Turkey},
pages = {1117--1120},
publisher = {{IEEE}},
year = {2000},
url = {https://doi.org/10.1109/ICASSP.2000.859160},
doi = {10.1109/ICASSP.2000.859160},
timestamp = {Thu, 23 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/SharmaEKJH00.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/HermanskyES00,
author = {Hynek Hermansky and
Daniel P. W. Ellis and
Sangita Sharma},
title = {Tandem connectionist feature extraction for conventional {HMM} systems},
booktitle = {{IEEE} International Conference on Acoustics, Speech, and Signal Processing.
{ICASSP} 2000, 5-9 June, 2000, Hilton Hotel and Convention Center,
Istanbul, Turkey},
pages = {1635--1638},
publisher = {{IEEE}},
year = {2000},
url = {https://doi.org/10.1109/ICASSP.2000.862024},
doi = {10.1109/ICASSP.2000.862024},
timestamp = {Thu, 23 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/HermanskyES00.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/SivadasJH00,
author = {Sunil Sivadas and
Pratibha Jain and
Hynek Hermansky},
title = {Discriminative MLPs in HMM-based recognition of speech in cellular
telephony},
booktitle = {Sixth International Conference on Spoken Language Processing, {ICSLP}
2000 / {INTERSPEECH} 2000, Beijing, China, October 16-20, 2000},
pages = {153--156},
publisher = {{ISCA}},
year = {2000},
url = {https://doi.org/10.21437/ICSLP.2000-774},
doi = {10.21437/ICSLP.2000-774},
timestamp = {Thu, 22 Jun 2023 16:42:19 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/SivadasJH00.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/JainH00,
author = {Pratibha Jain and
Hynek Hermansky},
title = {Temporal patterns of critical-band spectrum for text-to-speech},
booktitle = {Sixth International Conference on Spoken Language Processing, {ICSLP}
2000 / {INTERSPEECH} 2000, Beijing, China, October 16-20, 2000},
pages = {439--441},
publisher = {{ISCA}},
year = {2000},
url = {https://doi.org/10.21437/ICSLP.2000-301},
doi = {10.21437/ICSLP.2000-301},
timestamp = {Thu, 22 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/JainH00.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/KajarekarH00,
author = {Sachin S. Kajarekar and
Hynek Hermansky},
title = {Optimization of units for continuous-digit recognition task},
booktitle = {Sixth International Conference on Spoken Language Processing, {ICSLP}
2000 / {INTERSPEECH} 2000, Beijing, China, October 16-20, 2000},
pages = {539--542},
publisher = {{ISCA}},
year = {2000},
url = {https://doi.org/10.21437/ICSLP.2000-325},
doi = {10.21437/ICSLP.2000-325},
timestamp = {Thu, 22 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/KajarekarH00.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/tsd/KajarekarH00,
author = {Sachin S. Kajarekar and
Hynek Hermansky},
editor = {Petr Sojka and
Ivan Kopecek and
Karel Pala},
title = {Analysis of Information in Speech and Its Application in Speech Recognition},
booktitle = {Text, Speech and Dialogue - Third International Workshop, {TSD} 2000,
Brno, Czech Republic, September 13-16, 2000, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {1902},
pages = {283--288},
publisher = {Springer},
year = {2000},
url = {https://doi.org/10.1007/3-540-45323-7\_48},
doi = {10.1007/3-540-45323-7\_48},
timestamp = {Tue, 14 May 2019 10:00:45 +0200},
biburl = {https://dblp.org/rec/conf/tsd/KajarekarH00.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/speech/YegnanarayanaAHM99,
author = {B. Yegnanarayana and
Carlos Avenda{\~{n}}o and
Hynek Hermansky and
P. Satyanarayana Murthy},
title = {Speech enhancement using linear prediction residual},
journal = {Speech Commun.},
volume = {28},
number = {1},
pages = {25--42},
year = {1999},
url = {https://doi.org/10.1016/S0167-6393(98)00070-3},
doi = {10.1016/S0167-6393(98)00070-3},
timestamp = {Fri, 21 May 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/speech/YegnanarayanaAHM99.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/speech/KanederaAHP99,
author = {Noboru Kanedera and
Takayuki Arai and
Hynek Hermansky and
Misha Pavel},
title = {On the relative importance of various components of the modulation
spectrum for automatic speech recognition},
journal = {Speech Commun.},
volume = {28},
number = {1},
pages = {43--55},
year = {1999},
url = {https://doi.org/10.1016/S0167-6393(99)00002-3},
doi = {10.1016/S0167-6393(99)00002-3},
timestamp = {Sat, 22 Feb 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/speech/KanederaAHP99.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/YangVH99,
author = {Howard Hua Yang and
Sarel van Vuuren and
Hynek Hermansky},
title = {Relevancy of time-frequency features for phonetic classification measured
by mutual information},
booktitle = {Proceedings of the 1999 {IEEE} International Conference on Acoustics,
Speech, and Signal Processing, {ICASSP} '99, Phoenix, Arizona, USA,
March 15-19, 1999},
pages = {225--228},
publisher = {{IEEE} Computer Society},
year = {1999},
url = {https://doi.org/10.1109/ICASSP.1999.758103},
doi = {10.1109/ICASSP.1999.758103},
timestamp = {Thu, 23 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/YangVH99.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/HermanskyS99,
author = {Hynek Hermansky and
Sangita Sharma},
title = {Temporal patterns (TRAPs) in {ASR} of noisy speech},
booktitle = {Proceedings of the 1999 {IEEE} International Conference on Acoustics,
Speech, and Signal Processing, {ICASSP} '99, Phoenix, Arizona, USA,
March 15-19, 1999},
pages = {289--292},
publisher = {{IEEE} Computer Society},
year = {1999},
url = {https://doi.org/10.1109/ICASSP.1999.758119},
doi = {10.1109/ICASSP.1999.758119},
timestamp = {Thu, 23 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/HermanskyS99.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/HermanskyJ99,
author = {Hynek Hermansky and
Pratibha Jain},
title = {Down-sampling speech representation in {ASR}},
booktitle = {Sixth European Conference on Speech Communication and Technology,
{EUROSPEECH} 1999, Budapest, Hungary, September 5-9, 1999},
pages = {73--76},
publisher = {{ISCA}},
year = {1999},
url = {https://doi.org/10.21437/Eurospeech.1999-22},
doi = {10.21437/EUROSPEECH.1999-22},
timestamp = {Sat, 01 Jul 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/HermanskyJ99.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/KajarekarMH99,
author = {Sachin S. Kajarekar and
Narendranath Malayath and
Hynek Hermansky},
title = {Analysis of sources of variability in speech},
booktitle = {Sixth European Conference on Speech Communication and Technology,
{EUROSPEECH} 1999, Budapest, Hungary, September 5-9, 1999},
pages = {343--346},
publisher = {{ISCA}},
year = {1999},
url = {https://doi.org/10.21437/Eurospeech.1999-89},
doi = {10.21437/EUROSPEECH.1999-89},
timestamp = {Sat, 01 Jul 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/KajarekarMH99.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/VuurenH99,
author = {Sarel van Vuuren and
Hynek Hermansky},
title = {Speech variability in the modulation spectral domain - {SANOVA} technique
-},
booktitle = {Sixth European Conference on Speech Communication and Technology,
{EUROSPEECH} 1999, Budapest, Hungary, September 5-9, 1999},
pages = {2195--2198},
publisher = {{ISCA}},
year = {1999},
url = {https://doi.org/10.21437/Eurospeech.1999-486},
doi = {10.21437/EUROSPEECH.1999-486},
timestamp = {Sat, 01 Jul 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/VuurenH99.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/isspa/Hermansky99,
author = {Hynek Hermansky},
title = {The purpose, history, current state, and some evolving trends in feature
extraction for speech recognition},
booktitle = {{ISSPA} '99. Proceedings of the Fifth International Symposium on Signal
Processing and its Applications, Brisbane, QL, Australia, August 22-25,
1999},
pages = {6},
publisher = {{IEEE}},
year = {1999},
url = {https://doi.org/10.1109/ISSPA.1999.818095},
doi = {10.1109/ISSPA.1999.818095},
timestamp = {Wed, 16 Oct 2019 14:14:56 +0200},
biburl = {https://dblp.org/rec/conf/isspa/Hermansky99.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/YangH99,
author = {Howard Hua Yang and
Hynek Hermansky},
editor = {Sara A. Solla and
Todd K. Leen and
Klaus{-}Robert M{\"{u}}ller},
title = {Search for Information Bearing Components in Speech},
booktitle = {Advances in Neural Information Processing Systems 12, {[NIPS} Conference,
Denver, Colorado, USA, November 29 - December 4, 1999]},
pages = {803--812},
publisher = {The {MIT} Press},
year = {1999},
url = {http://papers.nips.cc/paper/1655-search-for-information-bearing-components-in-speech},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/YangH99.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/tsd/Hermansky99,
author = {Hynek Hermansky},
editor = {V{\'{a}}clav Matousek and
Pavel Mautner and
Jana Ocel{\'{\i}}kov{\'{a}} and
Petr Sojka},
title = {Data-Driven Analysis of Speech},
booktitle = {Text, Speech and Dialogue - Second International Workshop, TSD'99,
Plzen, Czech Republic, September 1999, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {1692},
pages = {10--18},
publisher = {Springer},
year = {1999},
url = {https://doi.org/10.1007/3-540-48239-3\_2},
doi = {10.1007/3-540-48239-3\_2},
timestamp = {Tue, 14 May 2019 10:00:45 +0200},
biburl = {https://dblp.org/rec/conf/tsd/Hermansky99.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/speech/Hermansky98,
author = {Hynek Hermansky},
title = {Should recognizers have ears?},
journal = {Speech Commun.},
volume = {25},
number = {1-3},
pages = {3--27},
year = {1998},
url = {https://doi.org/10.1016/S0167-6393(98)00027-2},
doi = {10.1016/S0167-6393(98)00027-2},
timestamp = {Sat, 22 Feb 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/speech/Hermansky98.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/YegnanarayanaMAH98,
author = {B. Yegnanarayana and
P. Satyanarayana Murthy and
Carlos Avenda{\~{n}}o and
Hynek Hermansky},
title = {Enhancement of reverberant speech using {LP} residual},
booktitle = {Proceedings of the 1998 {IEEE} International Conference on Acoustics,
Speech and Signal Processing, {ICASSP} '98, Seattle, Washington, USA,
May 12-15, 1998},
pages = {405--408},
publisher = {{IEEE}},
year = {1998},
url = {https://doi.org/10.1109/ICASSP.1998.674453},
doi = {10.1109/ICASSP.1998.674453},
timestamp = {Fri, 21 May 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/YegnanarayanaMAH98.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/KanederaHA98,
author = {Noboru Kanedera and
Hynek Hermansky and
Takayuki Arai},
title = {On properties of modulation spectrum for robust automatic speech recognition},
booktitle = {Proceedings of the 1998 {IEEE} International Conference on Acoustics,
Speech and Signal Processing, {ICASSP} '98, Seattle, Washington, USA,
May 12-15, 1998},
pages = {613--616},
publisher = {{IEEE}},
year = {1998},
url = {https://doi.org/10.1109/ICASSP.1998.675339},
doi = {10.1109/ICASSP.1998.675339},
timestamp = {Fri, 19 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/KanederaHA98.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/HermanskyM98,
author = {Hynek Hermansky and
Narendranath Malayath},
title = {Spectral basis functions from discriminant analysis},
booktitle = {The 5th International Conference on Spoken Language Processing, Incorporating
The 7th Australian International Speech Science and Technology Conference,
Sydney Convention Centre, Sydney, Australia, 30th November - 4th December
1998},
publisher = {{ISCA}},
year = {1998},
url = {https://doi.org/10.21437/ICSLP.1998-558},
doi = {10.21437/ICSLP.1998-558},
timestamp = {Thu, 22 Jun 2023 16:42:19 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/HermanskyM98.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/HermanskyS98,
author = {Hynek Hermansky and
Sangita Sharma},
title = {{TRAPS} - classifiers of temporal patterns},
booktitle = {The 5th International Conference on Spoken Language Processing, Incorporating
The 7th Australian International Speech Science and Technology Conference,
Sydney Convention Centre, Sydney, Australia, 30th November - 4th December
1998},
publisher = {{ISCA}},
year = {1998},
url = {https://doi.org/10.21437/ICSLP.1998-524},
doi = {10.21437/ICSLP.1998-524},
timestamp = {Thu, 22 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/HermanskyS98.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/VuurenH98,
author = {Sarel van Vuuren and
Hynek Hermansky},
title = {On the importance of components of the modulation spectrum for speaker
verification},
booktitle = {The 5th International Conference on Spoken Language Processing, Incorporating
The 7th Australian International Speech Science and Technology Conference,
Sydney Convention Centre, Sydney, Australia, 30th November - 4th December
1998},
publisher = {{ISCA}},
year = {1998},
url = {https://doi.org/10.21437/ICSLP.1998-258},
doi = {10.21437/ICSLP.1998-258},
timestamp = {Thu, 22 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/VuurenH98.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/taslp/AvendanoH97,
author = {Carlos Avenda{\~{n}}o and
Hynek Hermansky},
title = {On the effects of short-term spectrum smoothing in channel normalization},
journal = {{IEEE} Trans. Speech Audio Process.},
volume = {5},
number = {4},
pages = {372--374},
year = {1997},
url = {https://doi.org/10.1109/89.593318},
doi = {10.1109/89.593318},
timestamp = {Sun, 17 May 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/taslp/AvendanoH97.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/TibrewalaH97,
author = {Sangita Tibrewala and
Hynek Hermansky},
title = {Sub-band based recognition of noisy speech},
booktitle = {1997 {IEEE} International Conference on Acoustics, Speech, and Signal
Processing, {ICASSP} '97, Munich, Germany, April 21-24, 1997},
pages = {1255--1258},
publisher = {{IEEE} Computer Society},
year = {1997},
url = {https://doi.org/10.1109/ICASSP.1997.596173},
doi = {10.1109/ICASSP.1997.596173},
timestamp = {Thu, 23 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/TibrewalaH97.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/VuurenH97,
author = {Sarel van Vuuren and
Hynek Hermansky},
editor = {George Kokkinakis and
Nikos Fakotakis and
Evangelos Dermatas},
title = {Data-driven design of RASTA-like filters},
booktitle = {Fifth European Conference on Speech Communication and Technology,
{EUROSPEECH} 1997, Rhodes, Greece, September 22-25, 1997},
pages = {409--412},
publisher = {{ISCA}},
year = {1997},
url = {https://doi.org/10.21437/Eurospeech.1997-151},
doi = {10.21437/EUROSPEECH.1997-151},
timestamp = {Sun, 02 Jul 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/VuurenH97.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/MalayathHK97,
author = {Narendranath Malayath and
Hynek Hermansky and
Alexander Kain},
editor = {George Kokkinakis and
Nikos Fakotakis and
Evangelos Dermatas},
title = {Towards decomposing the sources of variability in speech},
booktitle = {Fifth European Conference on Speech Communication and Technology,
{EUROSPEECH} 1997, Rhodes, Greece, September 22-25, 1997},
pages = {497--500},
publisher = {{ISCA}},
year = {1997},
url = {https://doi.org/10.21437/Eurospeech.1997-167},
doi = {10.21437/EUROSPEECH.1997-167},
timestamp = {Sun, 02 Jul 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/MalayathHK97.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/KanederaAHP97,
author = {Noboru Kanedera and
Takayuki Arai and
Hynek Hermansky and
Misha Pavel},
editor = {George Kokkinakis and
Nikos Fakotakis and
Evangelos Dermatas},
title = {On the importance of various modulation frequencies for speech recognition},
booktitle = {Fifth European Conference on Speech Communication and Technology,
{EUROSPEECH} 1997, Rhodes, Greece, September 22-25, 1997},
pages = {1079--1082},
publisher = {{ISCA}},
year = {1997},
url = {https://doi.org/10.21437/Eurospeech.1997-104},
doi = {10.21437/EUROSPEECH.1997-104},
timestamp = {Sun, 02 Jul 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/KanederaAHP97.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/AvendanoTH97,
author = {Carlos Avenda{\~{n}}o and
Sangita Tibrewala and
Hynek Hermansky},
editor = {George Kokkinakis and
Nikos Fakotakis and
Evangelos Dermatas},
title = {Multiresolution channel normalization for {ASR} in reverberant environments},
booktitle = {Fifth European Conference on Speech Communication and Technology,
{EUROSPEECH} 1997, Rhodes, Greece, September 22-25, 1997},
pages = {1107--1110},
publisher = {{ISCA}},
year = {1997},
url = {https://doi.org/10.21437/Eurospeech.1997-111},
doi = {10.21437/EUROSPEECH.1997-111},
timestamp = {Sun, 02 Jul 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/AvendanoTH97.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/YegnanarayanaAHM97,
author = {B. Yegnanarayana and
Carlos Avenda{\~{n}}o and
Hynek Hermansky and
P. Satyanarayana Murthy},
editor = {George Kokkinakis and
Nikos Fakotakis and
Evangelos Dermatas},
title = {Processing linear prediction residual for speech enhancement},
booktitle = {Fifth European Conference on Speech Communication and Technology,
{EUROSPEECH} 1997, Rhodes, Greece, September 22-25, 1997},
pages = {1399--1402},
publisher = {{ISCA}},
year = {1997},
url = {https://doi.org/10.21437/Eurospeech.1997-390},
doi = {10.21437/EUROSPEECH.1997-390},
timestamp = {Sun, 02 Jul 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/YegnanarayanaAHM97.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/TibrewalaH97,
author = {Sangita Tibrewala and
Hynek Hermansky},
editor = {George Kokkinakis and
Nikos Fakotakis and
Evangelos Dermatas},
title = {Multi-band and adaptation approaches to robust speech recognition},
booktitle = {Fifth European Conference on Speech Communication and Technology,
{EUROSPEECH} 1997, Rhodes, Greece, September 22-25, 1997},
pages = {2619--2622},
publisher = {{ISCA}},
year = {1997},
url = {https://doi.org/10.21437/Eurospeech.1997-411},
doi = {10.21437/EUROSPEECH.1997-411},
timestamp = {Sun, 02 Jul 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/TibrewalaH97.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/speech/BourlardHM96,
author = {Herv{\'{e}} Bourlard and
Hynek Hermansky and
Nelson Morgan},
title = {Towards increasing speech recognition error rates},
journal = {Speech Commun.},
volume = {18},
number = {3},
pages = {205--231},
year = {1996},
url = {https://doi.org/10.1016/0167-6393(96)00003-9},
doi = {10.1016/0167-6393(96)00003-9},
timestamp = {Sat, 22 Feb 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/speech/BourlardHM96.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/eusipco/BourlardDHM96,
author = {Herv{\'{e}} Bourlard and
St{\'{e}}phane Dupont and
Hynek Hermansky and
Nelson Morgan},
title = {Towards subband-based speech recognition},
booktitle = {8th European Signal Processing Conference, {EUSIPCO} 1996, Trieste,
Italy, 10-13 September, 1996},
pages = {1--4},
publisher = {{IEEE}},
year = {1996},
url = {https://ieeexplore.ieee.org/document/7083216/},
timestamp = {Mon, 09 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/eusipco/BourlardDHM96.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/HermanskyTP96,
author = {Hynek Hermansky and
Sangita Tibrewala and
Misha Pavel},
title = {Towards {ASR} on partially corrupted speech},
booktitle = {The 4th International Conference on Spoken Language Processing, Philadelphia,
PA, USA, October 3-6, 1996},
pages = {462--465},
publisher = {{ISCA}},
year = {1996},
url = {https://doi.org/10.21437/ICSLP.1996-123},
doi = {10.21437/ICSLP.1996-123},
timestamp = {Thu, 22 Jun 2023 16:42:20 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/HermanskyTP96.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/AvendanoH96,
author = {Carlos Avenda{\~{n}}o and
Hynek Hermansky},
title = {Study on the dereverberation of speech based on temporal envelope
filtering},
booktitle = {The 4th International Conference on Spoken Language Processing, Philadelphia,
PA, USA, October 3-6, 1996},
pages = {889--892},
publisher = {{ISCA}},
year = {1996},
url = {https://doi.org/10.21437/ICSLP.1996-230},
doi = {10.21437/ICSLP.1996-230},
timestamp = {Thu, 22 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/AvendanoH96.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/AvendanoVH96,
author = {Carlos Avenda{\~{n}}o and
Sarel van Vuuren and
Hynek Hermansky},
title = {Data based filter design for RASTA-like channel normalization in {ASR}},
booktitle = {The 4th International Conference on Spoken Language Processing, Philadelphia,
PA, USA, October 3-6, 1996},
pages = {2087--2090},
publisher = {{ISCA}},
year = {1996},
url = {https://doi.org/10.21437/ICSLP.1996-529},
doi = {10.21437/ICSLP.1996-529},
timestamp = {Thu, 22 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/AvendanoVH96.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/AraiPHA96,
author = {Takayuki Arai and
Misha Pavel and
Hynek Hermansky and
Carlos Avenda{\~{n}}o},
title = {Intelligibility of speech with filtered time trajectories of spectral
envelopes},
booktitle = {The 4th International Conference on Spoken Language Processing, Philadelphia,
PA, USA, October 3-6, 1996},
pages = {2490--2493},
publisher = {{ISCA}},
year = {1996},
url = {https://doi.org/10.21437/ICSLP.1996-625},
doi = {10.21437/ICSLP.1996-625},
timestamp = {Thu, 22 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/AraiPHA96.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/taslp/ColeHABBBCCGHHLMMNOOPSSWWZZ95,
author = {Ronald A. Cole and
Lynette Hirschman and
Les E. Atlas and
Mary E. Beckman and
Alan Biermann and
Marcia A. Bush and
Mark Clements and
Jordan Cohen and
Oscar Garcia and
Brian A. Hanson and
Hynek Hermansky and
Steve Levinson and
Kathy McKeown and
Nelson Morgan and
David G. Novick and
Mari Ostendorf and
Sharon L. Oviatt and
Patti Price and
Harvey F. Silverman and
Judy Spitz and
Alex Waibel and
Clifford J. Weinstein and
Stephen A. Zahorian and
Victor Zue},
title = {The challenge of spoken language systems: research directions for
the nineties},
journal = {{IEEE} Trans. Speech Audio Process.},
volume = {3},
number = {1},
pages = {1--21},
year = {1995},
url = {https://doi.org/10.1109/89.365385},
doi = {10.1109/89.365385},
timestamp = {Sun, 17 May 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/taslp/ColeHABBBCCGHHLMMNOOPSSWWZZ95.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/MorganBGHW95,
author = {Nelson Morgan and
Herv{\'{e}} Bourlard and
Steven Greenberg and
Hynek Hermansky and
Su{-}Lin Wu},
title = {Stochastic perceptual models of speech},
booktitle = {1995 International Conference on Acoustics, Speech, and Signal Processing,
{ICASSP} '95, Detroit, Michigan, USA, May 08-12, 1995},
pages = {397--400},
publisher = {{IEEE} Computer Society},
year = {1995},
url = {https://doi.org/10.1109/ICASSP.1995.479605},
doi = {10.1109/ICASSP.1995.479605},
timestamp = {Thu, 23 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/MorganBGHW95.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/HermanskyWA95,
author = {Hynek Hermansky and
Eric A. Wan and
Carlos Avenda{\~{n}}o},
title = {Speech enhancement based on temporal processing},
booktitle = {1995 International Conference on Acoustics, Speech, and Signal Processing,
{ICASSP} '95, Detroit, Michigan, USA, May 08-12, 1995},
pages = {405--408},
publisher = {{IEEE} Computer Society},
year = {1995},
url = {https://doi.org/10.1109/ICASSP.1995.479607},
doi = {10.1109/ICASSP.1995.479607},
timestamp = {Thu, 23 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/HermanskyWA95.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/AvendanoHW95,
author = {Carlos Avenda{\~{n}}o and
Hynek Hermansky and
Eric A. Wan},
title = {Beyond {NYQUIST:} towards the recovery of broad-bandwidth speech from
narrow-bandwidth speech},
booktitle = {Fourth European Conference on Speech Communication and Technology,
{EUROSPEECH} 1995, Madrid, Spain, September 18-21, 1995},
pages = {165--168},
publisher = {{ISCA}},
year = {1995},
url = {https://doi.org/10.21437/Eurospeech.1995-44},
doi = {10.21437/EUROSPEECH.1995-44},
timestamp = {Sat, 01 Jul 2023 23:51:24 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/AvendanoHW95.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/taslp/HermanskyM94,
author = {Hynek Hermansky and
Nelson Morgan},
title = {{RASTA} processing of speech},
journal = {{IEEE} Trans. Speech Audio Process.},
volume = {2},
number = {4},
pages = {578--589},
year = {1994},
url = {https://doi.org/10.1109/89.326616},
doi = {10.1109/89.326616},
timestamp = {Sun, 17 May 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/taslp/HermanskyM94.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/KohlerMHHT94,
author = {Joachim Koehler and
Nelson Morgan and
Hynek Hermansky and
Hans{-}G{\"{u}}nter Hirsch and
Grace Tong},
title = {Integrating {RASTA-PLP} into speech recognition},
booktitle = {Proceedings of {ICASSP} '94: {IEEE} International Conference on Acoustics,
Speech and Signal Processing, Adelaide, South Australia, Australia,
April 19-22, 1994},
pages = {421--424},
publisher = {{IEEE} Computer Society},
year = {1994},
url = {https://doi.org/10.1109/ICASSP.1994.389266},
doi = {10.1109/ICASSP.1994.389266},
timestamp = {Thu, 23 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/KohlerMHHT94.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/MorganBGH94,
author = {Nelson Morgan and
Herv{\'{e}} Bourlard and
Steven Greenberg and
Hynek Hermansky},
title = {Stochastic perceptual auditory-event-based models for speech recognition},
booktitle = {The 3rd International Conference on Spoken Language Processing, {ICSLP}
1994, Yokohama, Japan, September 18-22, 1994},
pages = {1943--1946},
publisher = {{ISCA}},
year = {1994},
url = {https://doi.org/10.21437/ICSLP.1994-488},
doi = {10.21437/ICSLP.1994-488},
timestamp = {Wed, 21 Jun 2023 17:18:06 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/MorganBGH94.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/taslp/JunquaWH93,
author = {Jean{-}Claude Junqua and
Hisashi Wakita and
Hynek Hermansky},
title = {Evaluation and optimization of perceptually-based {ASR} front-end},
journal = {{IEEE} Trans. Speech Audio Process.},
volume = {1},
number = {1},
pages = {39--48},
year = {1993},
url = {https://doi.org/10.1109/89.221366},
doi = {10.1109/89.221366},
timestamp = {Sun, 17 May 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/taslp/JunquaWH93.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/HermanskyMH93,
author = {Hynek Hermansky and
Nelson Morgan and
Hans{-}G{\"{u}}nter Hirsch},
title = {Recognition of speech in additive and convolutional noise based on
{RASTA} spectral processing},
booktitle = {{IEEE} International Conference on Acoustics, Speech, and Signal Processing,
{ICASSP} '93, Minneapolis, Minnesota, USA, April 27-30, 1993},
pages = {83--86},
publisher = {{IEEE} Computer Society},
year = {1993},
url = {https://doi.ieeecomputersociety.org/10.1109/ICASSP.1993.319236},
doi = {10.1109/ICASSP.1993.319236},
timestamp = {Thu, 23 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/HermanskyMH93.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/HermanskyMBK92,
author = {Hynek Hermansky and
Nelson Morgan and
Aruna Bayya and
Phil Kohn},
title = {{RASTA-PLP} speech analysis technique},
booktitle = {1992 {IEEE} International Conference on Acoustics, Speech, and Signal
Processing, {ICASSP} '92, San Francisco, California, USA, March 23-26,
1992},
pages = {121--124},
publisher = {{IEEE} Computer Society},
year = {1992},
url = {https://doi.org/10.1109/ICASSP.1992.225957},
doi = {10.1109/ICASSP.1992.225957},
timestamp = {Mon, 09 Aug 2021 14:54:02 +0200},
biburl = {https://dblp.org/rec/conf/icassp/HermanskyMBK92.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/HermanskyM92,
author = {Hynek Hermansky and
Nelson Morgan},
title = {Towards handling the acoustic environment in spoken language processing},
booktitle = {The Second International Conference on Spoken Language Processing,
{ICSLP} 1992, Banff, Alberta, Canada, October 13-16, 1992},
pages = {85--88},
publisher = {{ISCA}},
year = {1992},
url = {https://doi.org/10.21437/ICSLP.1992-24},
doi = {10.21437/ICSLP.1992-24},
timestamp = {Wed, 21 Jun 2023 17:18:06 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/HermanskyM92.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/MorganHBKW91,
author = {Nelson Morgan and
Hynek Hermansky and
Herv{\'{e}} Bourlard and
Phil Kohn and
Chuck Wooters},
title = {Continuous speech recognition using {PLP} analysis with multilayer
perceptrons},
booktitle = {1991 International Conference on Acoustics, Speech, and Signal Processing,
{ICASSP} '91, Toronto, Ontario, Canada, May 14-17, 1991},
pages = {49--52},
publisher = {{IEEE} Computer Society},
year = {1991},
url = {https://doi.org/10.1109/ICASSP.1991.150275},
doi = {10.1109/ICASSP.1991.150275},
timestamp = {Sun, 02 Oct 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/MorganHBKW91.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/HermanskyC91,
author = {Hynek Hermansky and
Louis Anthony Cox Jr.},
title = {Perceptual linear predictive {(PLP)} analysis-resynthesis technique},
booktitle = {Second European Conference on Speech Communication and Technology,
{EUROSPEECH} 1991, Genova, Italy, September 24-26, 1991},
pages = {329--332},
publisher = {{ISCA}},
year = {1991},
url = {https://doi.org/10.21437/Eurospeech.1991-88},
doi = {10.21437/EUROSPEECH.1991-88},
timestamp = {Sun, 02 Jul 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/HermanskyC91.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/HermanskyMBK91,
author = {Hynek Hermansky and
Nelson Morgan and
Aruna Bayya and
Phil Kohn},
title = {Compensation for the effect of the communication channel in auditory-like
analysis of speech {(RASTA-PLP)}},
booktitle = {Second European Conference on Speech Communication and Technology,
{EUROSPEECH} 1991, Genova, Italy, September 24-26, 1991},
pages = {1367--1370},
publisher = {{ISCA}},
year = {1991},
url = {https://doi.org/10.21437/Eurospeech.1991-312},
doi = {10.21437/EUROSPEECH.1991-312},
timestamp = {Sun, 02 Jul 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/HermanskyMBK91.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/BayyaH90,
author = {Aruna Bayya and
Hynek Hermansky},
title = {Towards feature-based speech metric},
booktitle = {1990 International Conference on Acoustics, Speech, and Signal Processing,
{ICASSP} '90, Albuquerque, New Mexico, USA, April 3-6, 1990},
pages = {781--784},
publisher = {{IEEE}},
year = {1990},
url = {https://doi.org/10.1109/ICASSP.1990.115921},
doi = {10.1109/ICASSP.1990.115921},
timestamp = {Mon, 09 Aug 2021 14:54:02 +0200},
biburl = {https://dblp.org/rec/conf/icassp/BayyaH90.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/HermanskyB89,
author = {Hynek Hermansky and
David J. Broad},
title = {The effective second formant F2' and the vocal tract front-cavity},
booktitle = {{IEEE} International Conference on Acoustics, Speech, and Signal Processing,
{ICASSP} '89, Glasgow, Scotland, May 23-26, 1989},
pages = {480--483},
publisher = {{IEEE}},
year = {1989},
url = {https://doi.org/10.1109/ICASSP.1989.266468},
doi = {10.1109/ICASSP.1989.266468},
timestamp = {Mon, 09 Aug 2021 14:54:02 +0200},
biburl = {https://dblp.org/rec/conf/icassp/HermanskyB89.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/HermanskyJ88,
author = {Hynek Hermansky and
Jean{-}Claude Junqua},
title = {Optimization of perceptually-based {ASR} front-end [automatic speech
recognition]},
booktitle = {{IEEE} International Conference on Acoustics, Speech, and Signal Processing,
{ICASSP} '88, New York, New York, USA, April 11-14, 1988},
pages = {219--222},
publisher = {{IEEE}},
year = {1988},
url = {https://doi.org/10.1109/ICASSP.1988.196553},
doi = {10.1109/ICASSP.1988.196553},
timestamp = {Mon, 09 Aug 2021 14:54:02 +0200},
biburl = {https://dblp.org/rec/conf/icassp/HermanskyJ88.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/Hermansky87,
author = {Hynek Hermansky},
title = {An efficient speaker-independent automatic speech recognition by simulation
of some properties of human auditory perception},
booktitle = {{IEEE} International Conference on Acoustics, Speech, and Signal Processing,
{ICASSP} '87, Dallas, Texas, USA, April 6-9, 1987},
pages = {1159--1162},
publisher = {{IEEE}},
year = {1987},
url = {https://doi.org/10.1109/ICASSP.1987.1169803},
doi = {10.1109/ICASSP.1987.1169803},
timestamp = {Mon, 09 Aug 2021 14:54:02 +0200},
biburl = {https://dblp.org/rec/conf/icassp/Hermansky87.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/Hermansky87,
author = {Hynek Hermansky},
title = {Automatic speech recognition and human auditory perception},
booktitle = {European Conference on Speech Technology, {ECST} 1987, Edinburgh,
Scotland, UK, September 1987},
pages = {1079--1082},
publisher = {{ISCA}},
year = {1987},
url = {https://www.isca-speech.org/archive/ecst\_1987/hermansky87\_ecst.html},
timestamp = {Sun, 02 Jul 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/Hermansky87.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/HermanskyTMW86,
author = {Hynek Hermansky and
Kazuhiro Tsuga and
Shozo Makino and
Hisashi Wakita},
title = {Perceptually based processing in automatic speech recognition},
booktitle = {{IEEE} International Conference on Acoustics, Speech, and Signal Processing,
{ICASSP} 1986, Tokyo, Japan, April 7-11, 1986},
pages = {1971--1974},
publisher = {{IEEE}},
year = {1986},
url = {https://doi.org/10.1109/ICASSP.1986.1168649},
doi = {10.1109/ICASSP.1986.1168649},
timestamp = {Mon, 09 Aug 2021 14:54:02 +0200},
biburl = {https://dblp.org/rec/conf/icassp/HermanskyTMW86.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/speech/HermanskyHW85,
author = {Hynek Hermansky and
Brian A. Hanson and
Hisashi Wakita},
title = {Low-dimensional representation of vowels based on all-pole modeling
in the psychophysical domain},
journal = {Speech Commun.},
volume = {4},
number = {1-3},
pages = {181--187},
year = {1985},
url = {https://doi.org/10.1016/0167-6393(85)90045-7},
doi = {10.1016/0167-6393(85)90045-7},
timestamp = {Sat, 22 Feb 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/speech/HermanskyHW85.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/HermanskyHW85,
author = {Hynek Hermansky and
Brian A. Hanson and
Hisashi Wakita},
title = {Perceptually based linear predictive analysis of speech},
booktitle = {{IEEE} International Conference on Acoustics, Speech, and Signal Processing,
{ICASSP} '85, Tampa, Florida, USA, March 26-29, 1985},
pages = {509--512},
publisher = {{IEEE}},
year = {1985},
url = {https://doi.org/10.1109/ICASSP.1985.1168384},
doi = {10.1109/ICASSP.1985.1168384},
timestamp = {Mon, 09 Aug 2021 14:54:02 +0200},
biburl = {https://dblp.org/rec/conf/icassp/HermanskyHW85.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/HermanskyFS84,
author = {Hynek Hermansky and
Hiroya Fujisaki and
Yasuo Sato},
title = {Spectral envelope sampling and interpolation in linear predictive
analysis of speech},
booktitle = {{IEEE} International Conference on Acoustics, Speech, and Signal Processing,
{ICASSP} '84, San Diego, California, USA, March 19-21, 1984},
pages = {53--56},
publisher = {{IEEE}},
year = {1984},
url = {https://doi.org/10.1109/ICASSP.1984.1172421},
doi = {10.1109/ICASSP.1984.1172421},
timestamp = {Wed, 16 Oct 2019 14:14:52 +0200},
biburl = {https://dblp.org/rec/conf/icassp/HermanskyFS84.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/HermanskyFS83,
author = {Hynek Hermansky and
Hiroya Fujisaki and
Yasuo Sato},
title = {Analysis and synthesis of speech based on spectral transform linear
predictive method},
booktitle = {{IEEE} International Conference on Acoustics, Speech, and Signal Processing,
{ICASSP} '83, Boston, Massachusetts, USA, April 14-16, 1983},
pages = {777--780},
publisher = {{IEEE}},
year = {1983},
url = {https://doi.org/10.1109/ICASSP.1983.1172025},
doi = {10.1109/ICASSP.1983.1172025},
timestamp = {Wed, 16 Oct 2019 14:14:52 +0200},
biburl = {https://dblp.org/rec/conf/icassp/HermanskyFS83.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
a service of 
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
last updated on 2023-11-07 02:25 CET by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by:
