default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDBibTeX records: George Saon
@inproceedings{DBLP:conf/icassp/UdagawaSKMS24,
author = {Takuma Udagawa and
Masayuki Suzuki and
Gakuto Kurata and
Masayasu Muraoka and
George Saon},
title = {Multiple Representation Transfer from Large Language Models to End-to-End
{ASR} Systems},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2024, Seoul, Republic of Korea, April 14-19, 2024},
pages = {10176--10180},
publisher = {{IEEE}},
year = {2024},
url = {https://doi.org/10.1109/ICASSP48485.2024.10448022},
doi = {10.1109/ICASSP48485.2024.10448022},
timestamp = {Tue, 06 Aug 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/UdagawaSKMS24.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/AroraS0K24,
author = {Siddhant Arora and
George Saon and
Shinji Watanabe and
Brian Kingsbury},
title = {Semi-Autoregressive Streaming {ASR} with Label Context},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2024, Seoul, Republic of Korea, April 14-19, 2024},
pages = {11681--11685},
publisher = {{IEEE}},
year = {2024},
url = {https://doi.org/10.1109/ICASSP48485.2024.10446807},
doi = {10.1109/ICASSP48485.2024.10446807},
timestamp = {Wed, 07 Aug 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/AroraS0K24.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2402-00235,
author = {Ankit Gupta and
George Saon and
Brian Kingsbury},
title = {Exploring the limits of decoder-only models trained on public speech
recognition corpora},
journal = {CoRR},
volume = {abs/2402.00235},
year = {2024},
url = {https://doi.org/10.48550/arXiv.2402.00235},
doi = {10.48550/ARXIV.2402.00235},
eprinttype = {arXiv},
eprint = {2402.00235},
timestamp = {Fri, 09 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2402-00235.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/emnlp/MittalSJSK23,
author = {Ashish R. Mittal and
Sunita Sarawagi and
Preethi Jyothi and
George Saon and
Gakuto Kurata},
editor = {Houda Bouamor and
Juan Pino and
Kalika Bali},
title = {Speech-enriched Memory for Inference-time Adaptation of {ASR} Models
to Word Dictionaries},
booktitle = {Proceedings of the 2023 Conference on Empirical Methods in Natural
Language Processing, {EMNLP} 2023, Singapore, December 6-10, 2023},
pages = {14820--14835},
publisher = {Association for Computational Linguistics},
year = {2023},
url = {https://doi.org/10.18653/v1/2023.emnlp-main.916},
doi = {10.18653/V1/2023.EMNLP-MAIN.916},
timestamp = {Fri, 12 Apr 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/emnlp/MittalSJSK23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/SaonGC23,
author = {George Saon and
Ankit Gupta and
Xiaodong Cui},
title = {Diagonal State Space Augmented Transformers for Speech Recognition},
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/ICASSP49357.2023.10096271},
doi = {10.1109/ICASSP49357.2023.10096271},
timestamp = {Sun, 05 Nov 2023 16:51:21 +0100},
biburl = {https://dblp.org/rec/conf/icassp/SaonGC23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/ThomasKSK23,
author = {Samuel Thomas and
Hong{-}Kwang Jeff Kuo and
George Saon and
Brian Kingsbury},
title = {Multi-Speaker Data Augmentation for Improved end-to-end Automatic
Speech Recognition},
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/ICASSP49357.2023.10095622},
doi = {10.1109/ICASSP49357.2023.10095622},
timestamp = {Sun, 05 Nov 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/ThomasKSK23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/CuiSK23,
author = {Xiaodong Cui and
George Saon and
Brian Kingsbury},
editor = {Naomi Harte and
Julie Carson{-}Berndsen and
Gareth Jones},
title = {Improving {RNN} Transducer Acoustic Models for English Conversational
Speech Recognition},
booktitle = {24th Annual Conference of the International Speech Communication Association,
Interspeech 2023, Dublin, Ireland, August 20-24, 2023},
pages = {1299--1303},
publisher = {{ISCA}},
year = {2023},
url = {https://doi.org/10.21437/Interspeech.2023-2207},
doi = {10.21437/INTERSPEECH.2023-2207},
timestamp = {Fri, 14 Jun 2024 14:12:12 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/CuiSK23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2302-14120,
author = {George Saon and
Ankit Gupta and
Xiaodong Cui},
title = {Diagonal State Space Augmented Transformers for Speech Recognition},
journal = {CoRR},
volume = {abs/2302.14120},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2302.14120},
doi = {10.48550/ARXIV.2302.14120},
eprinttype = {arXiv},
eprint = {2302.14120},
timestamp = {Tue, 18 Apr 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2302-14120.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2309-04031,
author = {Takuma Udagawa and
Masayuki Suzuki and
Gakuto Kurata and
Masayasu Muraoka and
George Saon},
title = {Multiple Representation Transfer from Large Language Models to End-to-End
{ASR} Systems},
journal = {CoRR},
volume = {abs/2309.04031},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2309.04031},
doi = {10.48550/ARXIV.2309.04031},
eprinttype = {arXiv},
eprint = {2309.04031},
timestamp = {Tue, 12 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2309-04031.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2309-10926,
author = {Siddhant Arora and
George Saon and
Shinji Watanabe and
Brian Kingsbury},
title = {Semi-Autoregressive Streaming {ASR} With Label Context},
journal = {CoRR},
volume = {abs/2309.10926},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2309.10926},
doi = {10.48550/ARXIV.2309.10926},
eprinttype = {arXiv},
eprint = {2309.10926},
timestamp = {Mon, 25 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2309-10926.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2311-12727,
author = {Xiaodong Cui and
Ashish R. Mittal and
Songtao Lu and
Wei Zhang and
George Saon and
Brian Kingsbury},
title = {Soft Random Sampling: {A} Theoretical and Empirical Analysis},
journal = {CoRR},
volume = {abs/2311.12727},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2311.12727},
doi = {10.48550/ARXIV.2311.12727},
eprinttype = {arXiv},
eprint = {2311.12727},
timestamp = {Thu, 30 Nov 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2311-12727.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/BohnstinglGWSEP22,
author = {Thomas Bohnstingl and
Ayush Garg and
Stanislaw Wozniak and
George Saon and
Evangelos Eleftheriou and
Angeliki Pantazi},
title = {Speech Recognition Using Biologically-Inspired Neural Networks},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2022, Virtual and Singapore, 23-27 May 2022},
pages = {6992--6996},
publisher = {{IEEE}},
year = {2022},
url = {https://doi.org/10.1109/ICASSP43922.2022.9747499},
doi = {10.1109/ICASSP43922.2022.9747499},
timestamp = {Wed, 07 Dec 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/BohnstinglGWSEP22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/KuoTTKS22,
author = {Hong{-}Kwang Jeff Kuo and
Zolt{\'{a}}n T{\"{u}}ske and
Samuel Thomas and
Brian Kingsbury and
George Saon},
title = {Improving End-to-end Models for Set Prediction in Spoken Language
Understanding},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2022, Virtual and Singapore, 23-27 May 2022},
pages = {7162--7166},
publisher = {{IEEE}},
year = {2022},
url = {https://doi.org/10.1109/ICASSP43922.2022.9746086},
doi = {10.1109/ICASSP43922.2022.9746086},
timestamp = {Tue, 07 Jun 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/KuoTTKS22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/ThomasKKS22,
author = {Samuel Thomas and
Hong{-}Kwang Jeff Kuo and
Brian Kingsbury and
George Saon},
title = {Towards Reducing the Need for Speech Training Data to Build Spoken
Language Understanding Systems},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2022, Virtual and Singapore, 23-27 May 2022},
pages = {7932--7936},
publisher = {{IEEE}},
year = {2022},
url = {https://doi.org/10.1109/ICASSP43922.2022.9747555},
doi = {10.1109/ICASSP43922.2022.9747555},
timestamp = {Tue, 07 Jun 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/ThomasKKS22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/ThomasKSK22,
author = {Samuel Thomas and
Brian Kingsbury and
George Saon and
Hong{-}Kwang Jeff Kuo},
title = {Integrating Text Inputs for Training and Adapting {RNN} Transducer
{ASR} Models},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2022, Virtual and Singapore, 23-27 May 2022},
pages = {8127--8131},
publisher = {{IEEE}},
year = {2022},
url = {https://doi.org/10.1109/ICASSP43922.2022.9747862},
doi = {10.1109/ICASSP43922.2022.9747862},
timestamp = {Tue, 07 Jun 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/ThomasKSK22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/KonsAMDK0S22,
author = {Zvi Kons and
Hagai Aronowitz and
Edmilson da Silva Morais and
Matheus Damasceno and
Hong{-}Kwang Kuo and
Samuel Thomas and
George Saon},
editor = {Hanseok Ko and
John H. L. Hansen},
title = {Extending RNN-T-based speech recognition systems with emotion and
language classification},
booktitle = {23rd Annual Conference of the International Speech Communication Association,
Interspeech 2022, Incheon, Korea, September 18-22, 2022},
pages = {546--549},
publisher = {{ISCA}},
year = {2022},
url = {https://doi.org/10.21437/Interspeech.2022-10480},
doi = {10.21437/INTERSPEECH.2022-10480},
timestamp = {Tue, 11 Jun 2024 16:45:43 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/KonsAMDK0S22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/ShiSH0K22,
author = {Jiatong Shi and
George Saon and
David Haws and
Shinji Watanabe and
Brian Kingsbury},
editor = {Hanseok Ko and
John H. L. Hansen},
title = {{VQ-T:} {RNN} Transducers using Vector-Quantized Prediction Network
States},
booktitle = {23rd Annual Conference of the International Speech Communication Association,
Interspeech 2022, Incheon, Korea, September 18-22, 2022},
pages = {1656--1660},
publisher = {{ISCA}},
year = {2022},
url = {https://doi.org/10.21437/Interspeech.2022-414},
doi = {10.21437/INTERSPEECH.2022-414},
timestamp = {Wed, 21 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/ShiSH0K22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/FasoliCSVSCKG22,
author = {Andrea Fasoli and
Chia{-}Yu Chen and
Mauricio J. Serrano and
Swagath Venkataramani and
George Saon and
Xiaodong Cui and
Brian Kingsbury and
Kailash Gopalakrishnan},
editor = {Hanseok Ko and
John H. L. Hansen},
title = {Accelerating Inference and Language Model Fusion of Recurrent Neural
Network Transducers via End-to-End 4-bit Quantization},
booktitle = {23rd Annual Conference of the International Speech Communication Association,
Interspeech 2022, Incheon, Korea, September 18-22, 2022},
pages = {2038--2042},
publisher = {{ISCA}},
year = {2022},
url = {https://doi.org/10.21437/Interspeech.2022-413},
doi = {10.21437/INTERSPEECH.2022-413},
timestamp = {Wed, 21 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/FasoliCSVSCKG22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/CuiSNSFKK22,
author = {Xiaodong Cui and
George Saon and
Tohru Nagano and
Masayuki Suzuki and
Takashi Fukuda and
Brian Kingsbury and
Gakuto Kurata},
editor = {Hanseok Ko and
John H. L. Hansen},
title = {Improving Generalization of Deep Neural Network Acoustic Models with
Length Perturbation and N-best Based Label Smoothing},
booktitle = {23rd Annual Conference of the International Speech Communication Association,
Interspeech 2022, Incheon, Korea, September 18-22, 2022},
pages = {2638--2642},
publisher = {{ISCA}},
year = {2022},
url = {https://doi.org/10.21437/Interspeech.2022-821},
doi = {10.21437/INTERSPEECH.2022-821},
timestamp = {Wed, 21 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/CuiSNSFKK22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/Fukuda0SKSK22,
author = {Takashi Fukuda and
Samuel Thomas and
Masayuki Suzuki and
Gakuto Kurata and
George Saon and
Brian Kingsbury},
editor = {Hanseok Ko and
John H. L. Hansen},
title = {Global {RNN} Transducer Models For Multi-dialect Speech Recognition},
booktitle = {23rd Annual Conference of the International Speech Communication Association,
Interspeech 2022, Incheon, Korea, September 18-22, 2022},
pages = {3138--3142},
publisher = {{ISCA}},
year = {2022},
url = {https://doi.org/10.21437/Interspeech.2022-165},
doi = {10.21437/INTERSPEECH.2022-165},
timestamp = {Wed, 21 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/Fukuda0SKSK22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/UdagawaSKIS22,
author = {Takuma Udagawa and
Masayuki Suzuki and
Gakuto Kurata and
Nobuyasu Itoh and
George Saon},
editor = {Hanseok Ko and
John H. L. Hansen},
title = {Effect and Analysis of Large-scale Language Model Rescoring on Competitive
{ASR} Systems},
booktitle = {23rd Annual Conference of the International Speech Communication Association,
Interspeech 2022, Incheon, Korea, September 18-22, 2022},
pages = {3919--3923},
publisher = {{ISCA}},
year = {2022},
url = {https://doi.org/10.21437/Interspeech.2022-11123},
doi = {10.21437/INTERSPEECH.2022-11123},
timestamp = {Wed, 21 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/UdagawaSKIS22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2201-12105,
author = {Hong{-}Kwang Jeff Kuo and
Zolt{\'{a}}n T{\"{u}}ske and
Samuel Thomas and
Brian Kingsbury and
George Saon},
title = {Improving End-to-End Models for Set Prediction in Spoken Language
Understanding},
journal = {CoRR},
volume = {abs/2201.12105},
year = {2022},
url = {https://arxiv.org/abs/2201.12105},
eprinttype = {arXiv},
eprint = {2201.12105},
timestamp = {Wed, 02 Feb 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2201-12105.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2202-13155,
author = {Samuel Thomas and
Brian Kingsbury and
George Saon and
Hong{-}Kwang Jeff Kuo},
title = {Integrating Text Inputs For Training and Adapting {RNN} Transducer
{ASR} Models},
journal = {CoRR},
volume = {abs/2202.13155},
year = {2022},
url = {https://arxiv.org/abs/2202.13155},
eprinttype = {arXiv},
eprint = {2202.13155},
timestamp = {Wed, 02 Mar 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2202-13155.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2203-00006,
author = {Samuel Thomas and
Hong{-}Kwang Jeff Kuo and
Brian Kingsbury and
George Saon},
title = {Towards Reducing the Need for Speech Training Data To Build Spoken
Language Understanding Systems},
journal = {CoRR},
volume = {abs/2203.00006},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2203.00006},
doi = {10.48550/ARXIV.2203.00006},
eprinttype = {arXiv},
eprint = {2203.00006},
timestamp = {Wed, 16 Mar 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2203-00006.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2203-15176,
author = {Xiaodong Cui and
George Saon and
Tohru Nagano and
Masayuki Suzuki and
Takashi Fukuda and
Brian Kingsbury and
Gakuto Kurata},
title = {Improving Generalization of Deep Neural Network Acoustic Models with
Length Perturbation and N-best Based Label Smoothing},
journal = {CoRR},
volume = {abs/2203.15176},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2203.15176},
doi = {10.48550/ARXIV.2203.15176},
eprinttype = {arXiv},
eprint = {2203.15176},
timestamp = {Mon, 04 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2203-15176.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2204-00212,
author = {Takuma Udagawa and
Masayuki Suzuki and
Gakuto Kurata and
Nobuyasu Itoh and
George Saon},
title = {Effect and Analysis of Large-scale Language Model Rescoring on Competitive
{ASR} Systems},
journal = {CoRR},
volume = {abs/2204.00212},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2204.00212},
doi = {10.48550/ARXIV.2204.00212},
eprinttype = {arXiv},
eprint = {2204.00212},
timestamp = {Wed, 06 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2204-00212.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2206-07882,
author = {Andrea Fasoli and
Chia{-}Yu Chen and
Mauricio J. Serrano and
Swagath Venkataramani and
George Saon and
Xiaodong Cui and
Brian Kingsbury and
Kailash Gopalakrishnan},
title = {Accelerating Inference and Language Model Fusion of Recurrent Neural
Network Transducers via End-to-End 4-bit Quantization},
journal = {CoRR},
volume = {abs/2206.07882},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2206.07882},
doi = {10.48550/ARXIV.2206.07882},
eprinttype = {arXiv},
eprint = {2206.07882},
timestamp = {Tue, 21 Jun 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2206-07882.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2207-13965,
author = {Zvi Kons and
Hagai Aronowitz and
Edmilson da Silva Morais and
Matheus Damasceno and
Hong{-}Kwang Kuo and
Samuel Thomas and
George Saon},
title = {Extending RNN-T-based speech recognition systems with emotion and
language classification},
journal = {CoRR},
volume = {abs/2207.13965},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2207.13965},
doi = {10.48550/ARXIV.2207.13965},
eprinttype = {arXiv},
eprint = {2207.13965},
timestamp = {Tue, 02 Aug 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2207-13965.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2208-01818,
author = {Jiatong Shi and
George Saon and
David Haws and
Shinji Watanabe and
Brian Kingsbury},
title = {{VQ-T:} {RNN} Transducers using Vector-Quantized Prediction Network
States},
journal = {CoRR},
volume = {abs/2208.01818},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2208.01818},
doi = {10.48550/ARXIV.2208.01818},
eprinttype = {arXiv},
eprint = {2208.01818},
timestamp = {Tue, 21 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2208-01818.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/taslp/CuiZKLFKSK21,
author = {Xiaodong Cui and
Wei Zhang and
Abdullah Kayi and
Mingrui Liu and
Ulrich Finkler and
Brian Kingsbury and
George Saon and
David S. Kung},
title = {Asynchronous Decentralized Distributed Training of Acoustic Models},
journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.},
volume = {29},
pages = {3565--3576},
year = {2021},
url = {https://doi.org/10.1109/TASLP.2021.3122349},
doi = {10.1109/TASLP.2021.3122349},
timestamp = {Sat, 25 Dec 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/taslp/CuiZKLFKSK21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/SaonTBK21,
author = {George Saon and
Zolt{\'{a}}n T{\"{u}}ske and
Daniel Bola{\~{n}}os and
Brian Kingsbury},
title = {Advancing {RNN} Transducer Technology for Speech Recognition},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2021, Toronto, ON, Canada, June 6-11, 2021},
pages = {5654--5658},
publisher = {{IEEE}},
year = {2021},
url = {https://doi.org/10.1109/ICASSP39728.2021.9414716},
doi = {10.1109/ICASSP39728.2021.9414716},
timestamp = {Fri, 09 Jul 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/SaonTBK21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/0001KSTKKKH21,
author = {Samuel Thomas and
Hong{-}Kwang Jeff Kuo and
George Saon and
Zolt{\'{a}}n T{\"{u}}ske and
Brian Kingsbury and
Gakuto Kurata and
Zvi Kons and
Ron Hoory},
title = {{RNN} Transducer Models for Spoken Language Understanding},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2021, Toronto, ON, Canada, June 6-11, 2021},
pages = {7493--7497},
publisher = {{IEEE}},
year = {2021},
url = {https://doi.org/10.1109/ICASSP39728.2021.9414029},
doi = {10.1109/ICASSP39728.2021.9414029},
timestamp = {Fri, 09 Jul 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/0001KSTKKKH21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/Ganhotra0KJSTK21,
author = {Jatin Ganhotra and
Samuel Thomas and
Hong{-}Kwang Jeff Kuo and
Sachindra Joshi and
George Saon and
Zolt{\'{a}}n T{\"{u}}ske and
Brian Kingsbury},
editor = {Hynek Hermansky and
Honza Cernock{\'{y}} and
Luk{\'{a}}s Burget and
Lori Lamel and
Odette Scharenborg and
Petr Motl{\'{\i}}cek},
title = {Integrating Dialog History into End-to-End Spoken Language Understanding
Systems},
booktitle = {22nd Annual Conference of the International Speech Communication Association,
Interspeech 2021, Brno, Czechia, August 30 - September 3, 2021},
pages = {1254--1258},
publisher = {{ISCA}},
year = {2021},
url = {https://doi.org/10.21437/Interspeech.2021-1460},
doi = {10.21437/INTERSPEECH.2021-1460},
timestamp = {Tue, 11 Jun 2024 16:45:43 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/Ganhotra0KJSTK21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/CuiKSHT21,
author = {Xiaodong Cui and
Brian Kingsbury and
George Saon and
David Haws and
Zolt{\'{a}}n T{\"{u}}ske},
editor = {Hynek Hermansky and
Honza Cernock{\'{y}} and
Luk{\'{a}}s Burget and
Lori Lamel and
Odette Scharenborg and
Petr Motl{\'{\i}}cek},
title = {Reducing Exposure Bias in Training Recurrent Neural Network Transducers},
booktitle = {22nd Annual Conference of the International Speech Communication Association,
Interspeech 2021, Brno, Czechia, August 30 - September 3, 2021},
pages = {1802--1806},
publisher = {{ISCA}},
year = {2021},
url = {https://doi.org/10.21437/Interspeech.2021-587},
doi = {10.21437/INTERSPEECH.2021-587},
timestamp = {Wed, 21 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/CuiKSHT21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/KurataSKHT21,
author = {Gakuto Kurata and
George Saon and
Brian Kingsbury and
David Haws and
Zolt{\'{a}}n T{\"{u}}ske},
editor = {Hynek Hermansky and
Honza Cernock{\'{y}} and
Luk{\'{a}}s Burget and
Lori Lamel and
Odette Scharenborg and
Petr Motl{\'{\i}}cek},
title = {Improving Customization of Neural Transducers by Mitigating Acoustic
Mismatch of Synthesized Audio},
booktitle = {22nd Annual Conference of the International Speech Communication Association,
Interspeech 2021, Brno, Czechia, August 30 - September 3, 2021},
pages = {2027--2031},
publisher = {{ISCA}},
year = {2021},
url = {https://doi.org/10.21437/Interspeech.2021-1656},
doi = {10.21437/INTERSPEECH.2021-1656},
timestamp = {Wed, 21 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/KurataSKHT21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/TuskeSK21,
author = {Zolt{\'{a}}n T{\"{u}}ske and
George Saon and
Brian Kingsbury},
editor = {Hynek Hermansky and
Honza Cernock{\'{y}} and
Luk{\'{a}}s Burget and
Lori Lamel and
Odette Scharenborg and
Petr Motl{\'{\i}}cek},
title = {On the Limit of English Conversational Speech Recognition},
booktitle = {22nd Annual Conference of the International Speech Communication Association,
Interspeech 2021, Brno, Czechia, August 30 - September 3, 2021},
pages = {2062--2066},
publisher = {{ISCA}},
year = {2021},
url = {https://doi.org/10.21437/Interspeech.2021-211},
doi = {10.21437/INTERSPEECH.2021-211},
timestamp = {Wed, 21 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/TuskeSK21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/FasoliCSSWVSCK021,
author = {Andrea Fasoli and
Chia{-}Yu Chen and
Mauricio J. Serrano and
Xiao Sun and
Naigang Wang and
Swagath Venkataramani and
George Saon and
Xiaodong Cui and
Brian Kingsbury and
Wei Zhang and
Zolt{\'{a}}n T{\"{u}}ske and
Kailash Gopalakrishnan},
editor = {Hynek Hermansky and
Honza Cernock{\'{y}} and
Luk{\'{a}}s Burget and
Lori Lamel and
Odette Scharenborg and
Petr Motl{\'{\i}}cek},
title = {4-Bit Quantization of LSTM-Based Speech Recognition Models},
booktitle = {22nd Annual Conference of the International Speech Communication Association,
Interspeech 2021, Brno, Czechia, August 30 - September 3, 2021},
pages = {2586--2590},
publisher = {{ISCA}},
year = {2021},
url = {https://doi.org/10.21437/Interspeech.2021-1962},
doi = {10.21437/INTERSPEECH.2021-1962},
timestamp = {Sat, 19 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/FasoliCSSWVSCK021.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2103-09935,
author = {George Saon and
Zolt{\'{a}}n T{\"{u}}ske and
Daniel Bola{\~{n}}os and
Brian Kingsbury},
title = {Advancing {RNN} Transducer Technology for Speech Recognition},
journal = {CoRR},
volume = {abs/2103.09935},
year = {2021},
url = {https://arxiv.org/abs/2103.09935},
eprinttype = {arXiv},
eprint = {2103.09935},
timestamp = {Tue, 23 Mar 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2103-09935.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2104-03842,
author = {Samuel Thomas and
Hong{-}Kwang Jeff Kuo and
George Saon and
Zolt{\'{a}}n T{\"{u}}ske and
Brian Kingsbury and
Gakuto Kurata and
Zvi Kons and
Ron Hoory},
title = {{RNN} Transducer Models For Spoken Language Understanding},
journal = {CoRR},
volume = {abs/2104.03842},
year = {2021},
url = {https://arxiv.org/abs/2104.03842},
eprinttype = {arXiv},
eprint = {2104.03842},
timestamp = {Tue, 13 Apr 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2104-03842.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2105-00982,
author = {Zolt{\'{a}}n T{\"{u}}ske and
George Saon and
Brian Kingsbury},
title = {On the limit of English conversational speech recognition},
journal = {CoRR},
volume = {abs/2105.00982},
year = {2021},
url = {https://arxiv.org/abs/2105.00982},
eprinttype = {arXiv},
eprint = {2105.00982},
timestamp = {Wed, 12 May 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2105-00982.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2108-08405,
author = {Jatin Ganhotra and
Samuel Thomas and
Hong{-}Kwang Jeff Kuo and
Sachindra Joshi and
George Saon and
Zolt{\'{a}}n T{\"{u}}ske and
Brian Kingsbury},
title = {Integrating Dialog History into End-to-End Spoken Language Understanding
Systems},
journal = {CoRR},
volume = {abs/2108.08405},
year = {2021},
url = {https://arxiv.org/abs/2108.08405},
eprinttype = {arXiv},
eprint = {2108.08405},
timestamp = {Mon, 23 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2108-08405.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2108-10803,
author = {Xiaodong Cui and
Brian Kingsbury and
George Saon and
David Haws and
Zolt{\'{a}}n T{\"{u}}ske},
title = {Reducing Exposure Bias in Training Recurrent Neural Network Transducers},
journal = {CoRR},
volume = {abs/2108.10803},
year = {2021},
url = {https://arxiv.org/abs/2108.10803},
eprinttype = {arXiv},
eprint = {2108.10803},
timestamp = {Fri, 27 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2108-10803.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2108-12074,
author = {Andrea Fasoli and
Chia{-}Yu Chen and
Mauricio J. Serrano and
Xiao Sun and
Naigang Wang and
Swagath Venkataramani and
George Saon and
Xiaodong Cui and
Brian Kingsbury and
Wei Zhang and
Zolt{\'{a}}n T{\"{u}}ske and
Kailash Gopalakrishnan},
title = {4-bit Quantization of LSTM-based Speech Recognition Models},
journal = {CoRR},
volume = {abs/2108.12074},
year = {2021},
url = {https://arxiv.org/abs/2108.12074},
eprinttype = {arXiv},
eprint = {2108.12074},
timestamp = {Tue, 14 Dec 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2108-12074.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2110-02743,
author = {Thomas Bohnstingl and
Ayush Garg and
Stanislaw Wozniak and
George Saon and
Evangelos Eleftheriou and
Angeliki Pantazi},
title = {Towards efficient end-to-end speech recognition with biologically-inspired
neural networks},
journal = {CoRR},
volume = {abs/2110.02743},
year = {2021},
url = {https://arxiv.org/abs/2110.02743},
eprinttype = {arXiv},
eprint = {2110.02743},
timestamp = {Fri, 05 Nov 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2110-02743.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2110-11199,
author = {Xiaodong Cui and
Wei Zhang and
Abdullah Kayi and
Mingrui Liu and
Ulrich Finkler and
Brian Kingsbury and
George Saon and
David S. Kung},
title = {Asynchronous Decentralized Distributed Training of Acoustic Models},
journal = {CoRR},
volume = {abs/2110.11199},
year = {2021},
url = {https://arxiv.org/abs/2110.11199},
eprinttype = {arXiv},
eprint = {2110.11199},
timestamp = {Thu, 28 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2110-11199.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/spm/CuiZFSPK20,
author = {Xiaodong Cui and
Wei Zhang and
Ulrich Finkler and
George Saon and
Michael Picheny and
David S. Kung},
title = {Distributed Training of Deep Neural Network Acoustic Models for Automatic
Speech Recognition: {A} comparison of current training strategies},
journal = {{IEEE} Signal Process. Mag.},
volume = {37},
number = {3},
pages = {39--49},
year = {2020},
url = {https://doi.org/10.1109/MSP.2020.2969859},
doi = {10.1109/MSP.2020.2969859},
timestamp = {Wed, 23 Sep 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/spm/CuiZFSPK20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/ZhangCKLFKSMBDK20,
author = {Wei Zhang and
Xiaodong Cui and
Abdullah Kayi and
Mingrui Liu and
Ulrich Finkler and
Brian Kingsbury and
George Saon and
Youssef Mroueh and
Alper Buyuktosunoglu and
Payel Das and
David S. Kung and
Michael Picheny},
title = {Improving Efficiency in Large-Scale Decentralized Distributed Training},
booktitle = {2020 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2020, Barcelona, Spain, May 4-8, 2020},
pages = {3022--3026},
publisher = {{IEEE}},
year = {2020},
url = {https://doi.org/10.1109/ICASSP40776.2020.9054065},
doi = {10.1109/ICASSP40776.2020.9054065},
timestamp = {Wed, 23 Sep 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/ZhangCKLFKSMBDK20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/SaonTA20,
author = {George Saon and
Zolt{\'{a}}n T{\"{u}}ske and
Kartik Audhkhasi},
title = {Alignment-Length Synchronous Decoding for {RNN} Transducer},
booktitle = {2020 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2020, Barcelona, Spain, May 4-8, 2020},
pages = {7804--7808},
publisher = {{IEEE}},
year = {2020},
url = {https://doi.org/10.1109/ICASSP40776.2020.9053040},
doi = {10.1109/ICASSP40776.2020.9053040},
timestamp = {Thu, 23 Jul 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/SaonTA20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/TuskeSAK20,
author = {Zolt{\'{a}}n T{\"{u}}ske and
George Saon and
Kartik Audhkhasi and
Brian Kingsbury},
editor = {Helen Meng and
Bo Xu and
Thomas Fang Zheng},
title = {Single Headed Attention Based Sequence-to-Sequence Model for State-of-the-Art
Results on Switchboard},
booktitle = {21st Annual Conference of the International Speech Communication Association,
Interspeech 2020, Virtual Event, Shanghai, China, October 25-29, 2020},
pages = {551--555},
publisher = {{ISCA}},
year = {2020},
url = {https://doi.org/10.21437/Interspeech.2020-1488},
doi = {10.21437/INTERSPEECH.2020-1488},
timestamp = {Tue, 11 Jun 2024 16:45:43 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/TuskeSAK20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/KurataS20,
author = {Gakuto Kurata and
George Saon},
editor = {Helen Meng and
Bo Xu and
Thomas Fang Zheng},
title = {Knowledge Distillation from Offline to Streaming {RNN} Transducer
for End-to-End Speech Recognition},
booktitle = {21st Annual Conference of the International Speech Communication Association,
Interspeech 2020, Virtual Event, Shanghai, China, October 25-29, 2020},
pages = {2117--2121},
publisher = {{ISCA}},
year = {2020},
url = {https://doi.org/10.21437/Interspeech.2020-2442},
doi = {10.21437/INTERSPEECH.2020-2442},
timestamp = {Fri, 29 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/interspeech/KurataS20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2001-07263,
author = {Zolt{\'{a}}n T{\"{u}}ske and
George Saon and
Kartik Audhkhasi and
Brian Kingsbury},
title = {Single headed attention based sequence-to-sequence model for state-of-the-art
results on Switchboard-300},
journal = {CoRR},
volume = {abs/2001.07263},
year = {2020},
url = {https://arxiv.org/abs/2001.07263},
eprinttype = {arXiv},
eprint = {2001.07263},
timestamp = {Fri, 24 Jan 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2001-07263.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2002-01119,
author = {Wei Zhang and
Xiaodong Cui and
Abdullah Kayi and
Mingrui Liu and
Ulrich Finkler and
Brian Kingsbury and
George Saon and
Youssef Mroueh and
Alper Buyuktosunoglu and
Payel Das and
David S. Kung and
Michael Picheny},
title = {Improving Efficiency in Large-Scale Decentralized Distributed Training},
journal = {CoRR},
volume = {abs/2002.01119},
year = {2020},
url = {https://arxiv.org/abs/2002.01119},
eprinttype = {arXiv},
eprint = {2002.01119},
timestamp = {Wed, 23 Sep 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2002-01119.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2002-10502,
author = {Xiaodong Cui and
Wei Zhang and
Ulrich Finkler and
George Saon and
Michael Picheny and
David S. Kung},
title = {Distributed Training of Deep Neural Network Acoustic Models for Automatic
Speech Recognition},
journal = {CoRR},
volume = {abs/2002.10502},
year = {2020},
url = {https://arxiv.org/abs/2002.10502},
eprinttype = {arXiv},
eprint = {2002.10502},
timestamp = {Wed, 23 Sep 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2002-10502.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/asru/SaonTAKPT19,
author = {George Saon and
Zolt{\'{a}}n T{\"{u}}ske and
Kartik Audhkhasi and
Brian Kingsbury and
Michael Picheny and
Samuel Thomas},
title = {Simplified {LSTMS} for Speech Recognition},
booktitle = {{IEEE} Automatic Speech Recognition and Understanding Workshop, {ASRU}
2019, Singapore, December 14-18, 2019},
pages = {547--553},
publisher = {{IEEE}},
year = {2019},
url = {https://doi.org/10.1109/ASRU46091.2019.9003898},
doi = {10.1109/ASRU46091.2019.9003898},
timestamp = {Fri, 03 Jul 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/asru/SaonTAKPT19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/ZhangCFKSKP19,
author = {Wei Zhang and
Xiaodong Cui and
Ulrich Finkler and
Brian Kingsbury and
George Saon and
David S. Kung and
Michael Picheny},
title = {Distributed Deep Learning Strategies for Automatic Speech Recognition},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2019, Brighton, United Kingdom, May 12-17, 2019},
pages = {5706--5710},
publisher = {{IEEE}},
year = {2019},
url = {https://doi.org/10.1109/ICASSP.2019.8682888},
doi = {10.1109/ICASSP.2019.8682888},
timestamp = {Wed, 23 Sep 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/ZhangCFKSKP19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/SaonTAK19,
author = {George Saon and
Zolt{\'{a}}n T{\"{u}}ske and
Kartik Audhkhasi and
Brian Kingsbury},
title = {Sequence Noise Injected Training for 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 = {6261--6265},
publisher = {{IEEE}},
year = {2019},
url = {https://doi.org/10.1109/ICASSP.2019.8683706},
doi = {10.1109/ICASSP.2019.8683706},
timestamp = {Sun, 30 Jun 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/SaonTAK19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/ThomasSHKTSKPDK19,
author = {Samuel Thomas and
Masayuki Suzuki and
Yinghui Huang and
Gakuto Kurata and
Zolt{\'{a}}n T{\"{u}}ske and
George Saon and
Brian Kingsbury and
Michael Picheny and
Tom Dibert and
Alice Kaiser{-}Schatzlein and
Bern Samko},
title = {English Broadcast News Speech Recognition by Humans and Machines},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2019, Brighton, United Kingdom, May 12-17, 2019},
pages = {6455--6459},
publisher = {{IEEE}},
year = {2019},
url = {https://doi.org/10.1109/ICASSP.2019.8683211},
doi = {10.1109/ICASSP.2019.8683211},
timestamp = {Fri, 03 Jul 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/ThomasSHKTSKPDK19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/PichenyTKACS19,
author = {Michael Picheny and
Zolt{\'{a}}n T{\"{u}}ske and
Brian Kingsbury and
Kartik Audhkhasi and
Xiaodong Cui and
George Saon},
editor = {Gernot Kubin and
Zdravko Kacic},
title = {Challenging the Boundaries of Speech Recognition: The {MALACH} Corpus},
booktitle = {20th Annual Conference of the International Speech Communication Association,
Interspeech 2019, Graz, Austria, September 15-19, 2019},
pages = {326--330},
publisher = {{ISCA}},
year = {2019},
url = {https://doi.org/10.21437/Interspeech.2019-1907},
doi = {10.21437/INTERSPEECH.2019-1907},
timestamp = {Tue, 11 Jun 2024 16:45:43 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/PichenyTKACS19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/AudhkhasiSTKP19,
author = {Kartik Audhkhasi and
George Saon and
Zolt{\'{a}}n T{\"{u}}ske and
Brian Kingsbury and
Michael Picheny},
editor = {Gernot Kubin and
Zdravko Kacic},
title = {Forget a Bit to Learn Better: Soft Forgetting for CTC-Based Automatic
Speech Recognition},
booktitle = {20th Annual Conference of the International Speech Communication Association,
Interspeech 2019, Graz, Austria, September 15-19, 2019},
pages = {2618--2622},
publisher = {{ISCA}},
year = {2019},
url = {https://doi.org/10.21437/Interspeech.2019-2841},
doi = {10.21437/INTERSPEECH.2019-2841},
timestamp = {Fri, 29 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/interspeech/AudhkhasiSTKP19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/ZhangCFSKBK0P19,
author = {Wei Zhang and
Xiaodong Cui and
Ulrich Finkler and
George Saon and
Abdullah Kayi and
Alper Buyuktosunoglu and
Brian Kingsbury and
David S. Kung and
Michael Picheny},
editor = {Gernot Kubin and
Zdravko Kacic},
title = {A Highly Efficient Distributed Deep Learning System for Automatic
Speech Recognition},
booktitle = {20th Annual Conference of the International Speech Communication Association,
Interspeech 2019, Graz, Austria, September 15-19, 2019},
pages = {2628--2632},
publisher = {{ISCA}},
year = {2019},
url = {https://doi.org/10.21437/Interspeech.2019-2700},
doi = {10.21437/INTERSPEECH.2019-2700},
timestamp = {Fri, 29 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/interspeech/ZhangCFSKBK0P19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/TuskeAS19,
author = {Zolt{\'{a}}n T{\"{u}}ske and
Kartik Audhkhasi and
George Saon},
editor = {Gernot Kubin and
Zdravko Kacic},
title = {Advancing Sequence-to-Sequence Based Speech Recognition},
booktitle = {20th Annual Conference of the International Speech Communication Association,
Interspeech 2019, Graz, Austria, September 15-19, 2019},
pages = {3780--3784},
publisher = {{ISCA}},
year = {2019},
url = {https://doi.org/10.21437/Interspeech.2019-3018},
doi = {10.21437/INTERSPEECH.2019-3018},
timestamp = {Fri, 29 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/interspeech/TuskeAS19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1904-04956,
author = {Wei Zhang and
Xiaodong Cui and
Ulrich Finkler and
Brian Kingsbury and
George Saon and
David S. Kung and
Michael Picheny},
title = {Distributed Deep Learning Strategies For Automatic Speech Recognition},
journal = {CoRR},
volume = {abs/1904.04956},
year = {2019},
url = {http://arxiv.org/abs/1904.04956},
eprinttype = {arXiv},
eprint = {1904.04956},
timestamp = {Wed, 23 Sep 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1904-04956.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1904-13258,
author = {Samuel Thomas and
Masayuki Suzuki and
Yinghui Huang and
Gakuto Kurata and
Zolt{\'{a}}n T{\"{u}}ske and
George Saon and
Brian Kingsbury and
Michael Picheny and
Tom Dibert and
Alice Kaiser{-}Schatzlein and
Bern Samko},
title = {English Broadcast News Speech Recognition by Humans and Machines},
journal = {CoRR},
volume = {abs/1904.13258},
year = {2019},
url = {http://arxiv.org/abs/1904.13258},
eprinttype = {arXiv},
eprint = {1904.13258},
timestamp = {Fri, 03 Jul 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1904-13258.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1907-05701,
author = {Wei Zhang and
Xiaodong Cui and
Ulrich Finkler and
George Saon and
Abdullah Kayi and
Alper Buyuktosunoglu and
Brian Kingsbury and
David S. Kung and
Michael Picheny},
title = {A Highly Efficient Distributed Deep Learning System For Automatic
Speech Recognition},
journal = {CoRR},
volume = {abs/1907.05701},
year = {2019},
url = {http://arxiv.org/abs/1907.05701},
eprinttype = {arXiv},
eprint = {1907.05701},
timestamp = {Wed, 23 Sep 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1907-05701.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1908-03455,
author = {Michael Picheny and
Zolt{\'{a}}n T{\"{u}}ske and
Brian Kingsbury and
Kartik Audhkhasi and
Xiaodong Cui and
George Saon},
title = {Challenging the Boundaries of Speech Recognition: The {MALACH} Corpus},
journal = {CoRR},
volume = {abs/1908.03455},
year = {2019},
url = {http://arxiv.org/abs/1908.03455},
eprinttype = {arXiv},
eprint = {1908.03455},
timestamp = {Mon, 19 Aug 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1908-03455.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/AudhkhasiKRSP18,
author = {Kartik Audhkhasi and
Brian Kingsbury and
Bhuvana Ramabhadran and
George Saon and
Michael Picheny},
title = {Building Competitive Direct Acoustics-to-Word Models for English Conversational
Speech Recognition},
booktitle = {2018 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2018, Calgary, AB, Canada, April 15-20, 2018},
pages = {4759--4763},
publisher = {{IEEE}},
year = {2018},
url = {https://doi.org/10.1109/ICASSP.2018.8461935},
doi = {10.1109/ICASSP.2018.8461935},
timestamp = {Wed, 16 Oct 2019 14:14:52 +0200},
biburl = {https://dblp.org/rec/conf/icassp/AudhkhasiKRSP18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ibmrd/SaonP17,
author = {George Saon and
Michael Picheny},
title = {Recent advances in conversational speech recognition using convolutional
and recurrent neural networks},
journal = {{IBM} J. Res. Dev.},
volume = {61},
number = {4-5},
pages = {1:1--1:10},
year = {2017},
url = {https://doi.org/10.1147/JRD.2017.2701178},
doi = {10.1147/JRD.2017.2701178},
timestamp = {Sun, 08 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ibmrd/SaonP17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ibmrd/AudhkhasiRSSRCP17,
author = {Kartik Audhkhasi and
Andrew Rosenberg and
George Saon and
Abhinav Sethy and
Bhuvana Ramabhadran and
Stanley F. Chen and
Michael Picheny},
title = {Recent progress in deep end-to-end models for spoken language processing},
journal = {{IBM} J. Res. Dev.},
volume = {61},
number = {4-5},
pages = {2:1--2:10},
year = {2017},
url = {https://doi.org/10.1147/JRD.2017.2701207},
doi = {10.1147/JRD.2017.2701207},
timestamp = {Sun, 08 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ibmrd/AudhkhasiRSSRCP17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/asru/KurataRSS17,
author = {Gakuto Kurata and
Bhuvana Ramabhadran and
George Saon and
Abhinav Sethy},
title = {Language modeling with highway {LSTM}},
booktitle = {2017 {IEEE} Automatic Speech Recognition and Understanding Workshop,
{ASRU} 2017, Okinawa, Japan, December 16-20, 2017},
pages = {244--251},
publisher = {{IEEE}},
year = {2017},
url = {https://doi.org/10.1109/ASRU.2017.8268942},
doi = {10.1109/ASRU.2017.8268942},
timestamp = {Wed, 16 Oct 2019 14:14:51 +0200},
biburl = {https://dblp.org/rec/conf/asru/KurataRSS17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/CuiKRSSASNR17,
author = {Jia Cui and
Brian Kingsbury and
Bhuvana Ramabhadran and
George Saon and
Tom Sercu and
Kartik Audhkhasi and
Abhinav Sethy and
Markus Nu{\ss}baum{-}Thom and
Andrew Rosenberg},
title = {Knowledge distillation across ensembles of multilingual models for
low-resource languages},
booktitle = {2017 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2017, New Orleans, LA, USA, March 5-9, 2017},
pages = {4825--4829},
publisher = {{IEEE}},
year = {2017},
url = {https://doi.org/10.1109/ICASSP.2017.7953073},
doi = {10.1109/ICASSP.2017.7953073},
timestamp = {Wed, 16 Oct 2019 14:14:52 +0200},
biburl = {https://dblp.org/rec/conf/icassp/CuiKRSSASNR17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/SercuSCCRKS17,
author = {Tom Sercu and
George Saon and
Jia Cui and
Xiaodong Cui and
Bhuvana Ramabhadran and
Brian Kingsbury and
Abhinav Sethy},
title = {Network architectures for multilingual speech representation learning},
booktitle = {2017 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2017, New Orleans, LA, USA, March 5-9, 2017},
pages = {5295--5299},
publisher = {{IEEE}},
year = {2017},
url = {https://doi.org/10.1109/ICASSP.2017.7953167},
doi = {10.1109/ICASSP.2017.7953167},
timestamp = {Fri, 23 Jun 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/SercuSCCRKS17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/CuiGS17,
author = {Xiaodong Cui and
Vaibhava Goel and
George Saon},
editor = {Francisco Lacerda},
title = {Embedding-Based Speaker Adaptive Training of Deep Neural Networks},
booktitle = {18th Annual Conference of the International Speech Communication Association,
Interspeech 2017, Stockholm, Sweden, August 20-24, 2017},
pages = {122--126},
publisher = {{ISCA}},
year = {2017},
url = {https://doi.org/10.21437/Interspeech.2017-460},
doi = {10.21437/INTERSPEECH.2017-460},
timestamp = {Tue, 11 Jun 2024 16:45:43 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/CuiGS17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/SaonKSATDCRPLRH17,
author = {George Saon and
Gakuto Kurata and
Tom Sercu and
Kartik Audhkhasi and
Samuel Thomas and
Dimitrios Dimitriadis and
Xiaodong Cui and
Bhuvana Ramabhadran and
Michael Picheny and
Lynn{-}Li Lim and
Bergul Roomi and
Phil Hall},
editor = {Francisco Lacerda},
title = {English Conversational Telephone Speech Recognition by Humans and
Machines},
booktitle = {18th Annual Conference of the International Speech Communication Association,
Interspeech 2017, Stockholm, Sweden, August 20-24, 2017},
pages = {132--136},
publisher = {{ISCA}},
year = {2017},
url = {https://doi.org/10.21437/Interspeech.2017-405},
doi = {10.21437/INTERSPEECH.2017-405},
timestamp = {Mon, 26 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/SaonKSATDCRPLRH17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/KurataSRS17,
author = {Gakuto Kurata and
Abhinav Sethy and
Bhuvana Ramabhadran and
George Saon},
editor = {Francisco Lacerda},
title = {Empirical Exploration of Novel Architectures and Objectives for Language
Models},
booktitle = {18th Annual Conference of the International Speech Communication Association,
Interspeech 2017, Stockholm, Sweden, August 20-24, 2017},
pages = {279--283},
publisher = {{ISCA}},
year = {2017},
url = {https://doi.org/10.21437/Interspeech.2017-723},
doi = {10.21437/INTERSPEECH.2017-723},
timestamp = {Mon, 26 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/KurataSRS17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/AudhkhasiRSPN17,
author = {Kartik Audhkhasi and
Bhuvana Ramabhadran and
George Saon and
Michael Picheny and
David Nahamoo},
editor = {Francisco Lacerda},
title = {Direct Acoustics-to-Word Models for English Conversational Speech
Recognition},
booktitle = {18th Annual Conference of the International Speech Communication Association,
Interspeech 2017, Stockholm, Sweden, August 20-24, 2017},
pages = {959--963},
publisher = {{ISCA}},
year = {2017},
url = {https://doi.org/10.21437/Interspeech.2017-546},
doi = {10.21437/INTERSPEECH.2017-546},
timestamp = {Mon, 26 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/AudhkhasiRSPN17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/CongKGSZ17,
author = {Guojing Cong and
Brian Kingsbury and
Soumyadip Gosh and
George Saon and
Fan Zhou},
title = {Accelerating deep neural network learning for speech recognition on
a cluster of GPUs},
booktitle = {Proceedings of the Machine Learning on {HPC} Environments, MLHPC@SC
2017, Denver, CO, USA, November 13, 2017},
pages = {3:1--3:8},
publisher = {{ACM}},
year = {2017},
url = {https://doi.org/10.1145/3146347.3146351},
doi = {10.1145/3146347.3146351},
timestamp = {Tue, 13 Dec 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/sc/CongKGSZ17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/SaonKSATDCRPLRH17,
author = {George Saon and
Gakuto Kurata and
Tom Sercu and
Kartik Audhkhasi and
Samuel Thomas and
Dimitrios Dimitriadis and
Xiaodong Cui and
Bhuvana Ramabhadran and
Michael Picheny and
Lynn{-}Li Lim and
Bergul Roomi and
Phil Hall},
title = {English Conversational Telephone Speech Recognition by Humans and
Machines},
journal = {CoRR},
volume = {abs/1703.02136},
year = {2017},
url = {http://arxiv.org/abs/1703.02136},
eprinttype = {arXiv},
eprint = {1703.02136},
timestamp = {Fri, 03 Jul 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/SaonKSATDCRPLRH17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/AudhkhasiRSPN17,
author = {Kartik Audhkhasi and
Bhuvana Ramabhadran and
George Saon and
Michael Picheny and
David Nahamoo},
title = {Direct Acoustics-to-Word Models for English Conversational Speech
Recognition},
journal = {CoRR},
volume = {abs/1703.07754},
year = {2017},
url = {http://arxiv.org/abs/1703.07754},
eprinttype = {arXiv},
eprint = {1703.07754},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/AudhkhasiRSPN17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1709-06436,
author = {Gakuto Kurata and
Bhuvana Ramabhadran and
George Saon and
Abhinav Sethy},
title = {Language Modeling with Highway {LSTM}},
journal = {CoRR},
volume = {abs/1709.06436},
year = {2017},
url = {http://arxiv.org/abs/1709.06436},
eprinttype = {arXiv},
eprint = {1709.06436},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1709-06436.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1710-06937,
author = {Xiaodong Cui and
Vaibhava Goel and
George Saon},
title = {Embedding-Based Speaker Adaptive Training of Deep Neural Networks},
journal = {CoRR},
volume = {abs/1710.06937},
year = {2017},
url = {http://arxiv.org/abs/1710.06937},
eprinttype = {arXiv},
eprint = {1710.06937},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1710-06937.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1712-03133,
author = {Kartik Audhkhasi and
Brian Kingsbury and
Bhuvana Ramabhadran and
George Saon and
Michael Picheny},
title = {Building competitive direct acoustics-to-word models for English conversational
speech recognition},
journal = {CoRR},
volume = {abs/1712.03133},
year = {2017},
url = {http://arxiv.org/abs/1712.03133},
eprinttype = {arXiv},
eprint = {1712.03133},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1712-03133.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/HawsDSTP16,
author = {David Haws and
Dimitrios Dimitriadis and
George Saon and
Samuel Thomas and
Michael Picheny},
title = {On the importance of event detection for {ASR}},
booktitle = {2016 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2016, Shanghai, China, March 20-25, 2016},
pages = {5705--5709},
publisher = {{IEEE}},
year = {2016},
url = {https://doi.org/10.1109/ICASSP.2016.7472770},
doi = {10.1109/ICASSP.2016.7472770},
timestamp = {Fri, 03 Jul 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/HawsDSTP16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/SaonSRK16,
author = {George Saon and
Tom Sercu and
Steven J. Rennie and
Hong{-}Kwang Jeff Kuo},
editor = {Nelson Morgan},
title = {The {IBM} 2016 English Conversational Telephone Speech Recognition
System},
booktitle = {17th Annual Conference of the International Speech Communication Association,
Interspeech 2016, San Francisco, CA, USA, September 8-12, 2016},
pages = {7--11},
publisher = {{ISCA}},
year = {2016},
url = {https://doi.org/10.21437/Interspeech.2016-1460},
doi = {10.21437/INTERSPEECH.2016-1460},
timestamp = {Tue, 11 Jun 2024 16:45:43 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/SaonSRK16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/SuzukiTTRS16,
author = {Masayuki Suzuki and
Ryuki Tachibana and
Samuel Thomas and
Bhuvana Ramabhadran and
George Saon},
editor = {Nelson Morgan},
title = {Domain Adaptation of {CNN} Based Acoustic Models Under Limited Resource
Settings},
booktitle = {17th Annual Conference of the International Speech Communication Association,
Interspeech 2016, San Francisco, CA, USA, September 8-12, 2016},
pages = {1588--1592},
publisher = {{ISCA}},
year = {2016},
url = {https://doi.org/10.21437/Interspeech.2016-1161},
doi = {10.21437/INTERSPEECH.2016-1161},
timestamp = {Fri, 29 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/interspeech/SuzukiTTRS16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/SaonSRK16,
author = {George Saon and
Tom Sercu and
Steven J. Rennie and
Hong{-}Kwang Jeff Kuo},
title = {The {IBM} 2016 English Conversational Telephone Speech Recognition
System},
journal = {CoRR},
volume = {abs/1604.08242},
year = {2016},
url = {http://arxiv.org/abs/1604.08242},
eprinttype = {arXiv},
eprint = {1604.08242},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/SaonSRK16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/nn/SainathKSSMDR15,
author = {Tara N. Sainath and
Brian Kingsbury and
George Saon and
Hagen Soltau and
Abdel{-}rahman Mohamed and
George E. Dahl and
Bhuvana Ramabhadran},
title = {Deep Convolutional Neural Networks for Large-scale Speech Tasks},
journal = {Neural Networks},
volume = {64},
pages = {39--48},
year = {2015},
url = {https://doi.org/10.1016/j.neunet.2014.08.005},
doi = {10.1016/J.NEUNET.2014.08.005},
timestamp = {Wed, 14 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/nn/SainathKSSMDR15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/ThomasSSN15,
author = {Samuel Thomas and
George Saon and
Maarten Van Segbroeck and
Shrikanth S. Narayanan},
title = {Improvements to the {IBM} speech activity detection system for the
{DARPA} {RATS} program},
booktitle = {2015 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2015, South Brisbane, Queensland, Australia,
April 19-24, 2015},
pages = {4500--4504},
publisher = {{IEEE}},
year = {2015},
url = {https://doi.org/10.1109/ICASSP.2015.7178822},
doi = {10.1109/ICASSP.2015.7178822},
timestamp = {Fri, 03 Jul 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/ThomasSSN15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/KeskarS15,
author = {Nitish Shirish Keskar and
George Saon},
title = {A nonmonotone learning rate strategy for {SGD} training of deep neural
networks},
booktitle = {2015 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2015, South Brisbane, Queensland, Australia,
April 19-24, 2015},
pages = {4974--4978},
publisher = {{IEEE}},
year = {2015},
url = {https://doi.org/10.1109/ICASSP.2015.7178917},
doi = {10.1109/ICASSP.2015.7178917},
timestamp = {Fri, 19 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/KeskarS15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/ManguSPK15,
author = {Lidia Mangu and
George Saon and
Michael Picheny and
Brian Kingsbury},
title = {Order-free spoken term detection},
booktitle = {2015 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2015, South Brisbane, Queensland, Australia,
April 19-24, 2015},
pages = {5331--5335},
publisher = {{IEEE}},
year = {2015},
url = {https://doi.org/10.1109/ICASSP.2015.7178989},
doi = {10.1109/ICASSP.2015.7178989},
timestamp = {Fri, 19 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/ManguSPK15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/SaonKRP15,
author = {George Saon and
Hong{-}Kwang Jeff Kuo and
Steven J. Rennie and
Michael Picheny},
title = {The {IBM} 2015 English conversational telephone speech recognition
system},
booktitle = {16th Annual Conference of the International Speech Communication Association,
{INTERSPEECH} 2015, Dresden, Germany, September 6-10, 2015},
pages = {3140--3144},
publisher = {{ISCA}},
year = {2015},
url = {https://doi.org/10.21437/Interspeech.2015-632},
doi = {10.21437/INTERSPEECH.2015-632},
timestamp = {Tue, 11 Jun 2024 16:45:43 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/SaonKRP15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/ThomasSKM15,
author = {Samuel Thomas and
George Saon and
Hong{-}Kwang Jeff Kuo and
Lidia Mangu},
title = {The {IBM} {BOLT} speech transcription system},
booktitle = {16th Annual Conference of the International Speech Communication Association,
{INTERSPEECH} 2015, Dresden, Germany, September 6-10, 2015},
pages = {3150--3153},
publisher = {{ISCA}},
year = {2015},
url = {https://doi.org/10.21437/Interspeech.2015-634},
doi = {10.21437/INTERSPEECH.2015-634},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/ThomasSKM15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/CuiSRK15,
author = {Jia Cui and
George Saon and
Bhuvana Ramabhadran and
Brian Kingsbury},
title = {A multi-region deep neural network model in speech recognition},
booktitle = {16th Annual Conference of the International Speech Communication Association,
{INTERSPEECH} 2015, Dresden, Germany, September 6-10, 2015},
pages = {3244--3248},
publisher = {{ISCA}},
year = {2015},
url = {https://doi.org/10.21437/Interspeech.2015-653},
doi = {10.21437/INTERSPEECH.2015-653},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/CuiSRK15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/SaonKRP15,
author = {George Saon and
Hong{-}Kwang Jeff Kuo and
Steven J. Rennie and
Michael Picheny},
title = {The {IBM} 2015 English Conversational Telephone Speech Recognition
System},
journal = {CoRR},
volume = {abs/1505.05899},
year = {2015},
url = {http://arxiv.org/abs/1505.05899},
eprinttype = {arXiv},
eprint = {1505.05899},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/SaonKRP15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/ThomasGSS14,
author = {Samuel Thomas and
Sriram Ganapathy and
George Saon and
Hagen Soltau},
title = {Analyzing convolutional neural networks for speech activity detection
in mismatched acoustic conditions},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2014, Florence, Italy, May 4-9, 2014},
pages = {2519--2523},
publisher = {{IEEE}},
year = {2014},
url = {https://doi.org/10.1109/ICASSP.2014.6854054},
doi = {10.1109/ICASSP.2014.6854054},
timestamp = {Fri, 03 Jul 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/ThomasGSS14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/SaonS14,
author = {George Saon and
Hagen Soltau},
title = {A comparison of two optimization techniques for sequence discriminative
training of deep neural networks},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2014, Florence, Italy, May 4-9, 2014},
pages = {5567--5571},
publisher = {{IEEE}},
year = {2014},
url = {https://doi.org/10.1109/ICASSP.2014.6854668},
doi = {10.1109/ICASSP.2014.6854668},
timestamp = {Fri, 19 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/SaonS14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/SoltauSS14,
author = {Hagen Soltau and
George Saon and
Tara N. Sainath},
title = {Joint training of convolutional and non-convolutional neural networks},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2014, Florence, Italy, May 4-9, 2014},
pages = {5572--5576},
publisher = {{IEEE}},
year = {2014},
url = {https://doi.org/10.1109/ICASSP.2014.6854669},
doi = {10.1109/ICASSP.2014.6854669},
timestamp = {Fri, 19 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/SoltauSS14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/SainathKMSR14,
author = {Tara N. Sainath and
Brian Kingsbury and
Abdel{-}rahman Mohamed and
George Saon and
Bhuvana Ramabhadran},
title = {Improvements to filterbank and delta learning within a deep neural
network framework},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2014, Florence, Italy, May 4-9, 2014},
pages = {6839--6843},
publisher = {{IEEE}},
year = {2014},
url = {https://doi.org/10.1109/ICASSP.2014.6854925},
doi = {10.1109/ICASSP.2014.6854925},
timestamp = {Fri, 19 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/SainathKMSR14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/SaonSEP14,
author = {George Saon and
Hagen Soltau and
Ahmad Emami and
Michael Picheny},
editor = {Haizhou Li and
Helen M. Meng and
Bin Ma and
Engsiong Chng and
Lei Xie},
title = {Unfolded recurrent neural networks for speech recognition},
booktitle = {15th Annual Conference of the International Speech Communication Association,
{INTERSPEECH} 2014, Singapore, September 14-18, 2014},
pages = {343--347},
publisher = {{ISCA}},
year = {2014},
url = {https://doi.org/10.21437/Interspeech.2014-81},
doi = {10.21437/INTERSPEECH.2014-81},
timestamp = {Tue, 11 Jun 2024 16:45:43 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/SaonSEP14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/SainathCRPGKSAC14,
author = {Tara N. Sainath and
I{-}Hsin Chung and
Bhuvana Ramabhadran and
Michael Picheny and
John A. Gunnels and
Brian Kingsbury and
George Saon and
Vernon Austel and
Upendra V. Chaudhari},
editor = {Haizhou Li and
Helen M. Meng and
Bin Ma and
Engsiong Chng and
Lei Xie},
title = {Parallel deep neural network training for {LVCSR} tasks using blue
gene/Q},
booktitle = {15th Annual Conference of the International Speech Communication Association,
{INTERSPEECH} 2014, Singapore, September 14-18, 2014},
pages = {1048--1052},
publisher = {{ISCA}},
year = {2014},
url = {https://doi.org/10.21437/Interspeech.2014-272},
doi = {10.21437/INTERSPEECH.2014-272},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/SainathCRPGKSAC14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/slt/Saon14,
author = {George Saon},
title = {A distributed architecture for fast {SGD} sequence discriminative
training of {DNN} acoustic models},
booktitle = {2014 {IEEE} Spoken Language Technology Workshop, {SLT} 2014, South
Lake Tahoe, NV, USA, December 7-10, 2014},
pages = {183--188},
publisher = {{IEEE}},
year = {2014},
url = {https://doi.org/10.1109/SLT.2014.7078571},
doi = {10.1109/SLT.2014.7078571},
timestamp = {Wed, 16 Oct 2019 14:14:53 +0200},
biburl = {https://dblp.org/rec/conf/slt/Saon14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@incollection{DBLP:series/tanlp/SoltauSMKKCB14,
author = {Hagen Soltau and
George Saon and
Lidia Mangu and
Hong{-}Kwang Kuo and
Brian Kingsbury and
Stephen M. Chu and
Fadi Biadsy},
editor = {Imed Zitouni},
title = {Automatic Speech Recognition},
booktitle = {Natural Language Processing of Semitic Languages},
series = {Theory and Applications of Natural Language Processing},
pages = {409--459},
publisher = {Springer},
year = {2014},
url = {https://doi.org/10.1007/978-3-642-45358-8\_13},
doi = {10.1007/978-3-642-45358-8\_13},
timestamp = {Wed, 06 Mar 2019 11:14:32 +0100},
biburl = {https://dblp.org/rec/series/tanlp/SoltauSMKKCB14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/asru/SaonSNP13,
author = {George Saon and
Hagen Soltau and
David Nahamoo and
Michael Picheny},
title = {Speaker adaptation of neural network acoustic models using i-vectors},
booktitle = {2013 {IEEE} Workshop on Automatic Speech Recognition and Understanding,
Olomouc, Czech Republic, December 8-12, 2013},
pages = {55--59},
publisher = {{IEEE}},
year = {2013},
url = {https://doi.org/10.1109/ASRU.2013.6707705},
doi = {10.1109/ASRU.2013.6707705},
timestamp = {Wed, 16 Oct 2019 14:14:51 +0200},
biburl = {https://dblp.org/rec/conf/asru/SaonSNP13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/asru/ManguSKS13,
author = {Lidia Mangu and
Hagen Soltau and
Hong{-}Kwang Kuo and
George Saon},
title = {The {IBM} keyword search system for the {DARPA} {RATS} program},
booktitle = {2013 {IEEE} Workshop on Automatic Speech Recognition and Understanding,
Olomouc, Czech Republic, December 8-12, 2013},
pages = {204--209},
publisher = {{IEEE}},
year = {2013},
url = {https://doi.org/10.1109/ASRU.2013.6707730},
doi = {10.1109/ASRU.2013.6707730},
timestamp = {Fri, 26 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/asru/ManguSKS13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/asru/SainathKMDSSBAR13,
author = {Tara N. Sainath and
Brian Kingsbury and
Abdel{-}rahman Mohamed and
George E. Dahl and
George Saon and
Hagen Soltau and
Tom{\'{a}}s Beran and
Aleksandr Y. Aravkin and
Bhuvana Ramabhadran},
title = {Improvements to Deep Convolutional Neural Networks for {LVCSR}},
booktitle = {2013 {IEEE} Workshop on Automatic Speech Recognition and Understanding,
Olomouc, Czech Republic, December 8-12, 2013},
pages = {315--320},
publisher = {{IEEE}},
year = {2013},
url = {https://doi.org/10.1109/ASRU.2013.6707749},
doi = {10.1109/ASRU.2013.6707749},
timestamp = {Fri, 26 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/asru/SainathKMDSSBAR13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/ManguSKKS13,
author = {Lidia Mangu and
Hagen Soltau and
Hong{-}Kwang Kuo and
Brian Kingsbury and
George Saon},
title = {Exploiting diversity for spoken term detection},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2013, Vancouver, BC, Canada, May 26-31, 2013},
pages = {8282--8286},
publisher = {{IEEE}},
year = {2013},
url = {https://doi.org/10.1109/ICASSP.2013.6639280},
doi = {10.1109/ICASSP.2013.6639280},
timestamp = {Wed, 16 Oct 2019 14:14:52 +0200},
biburl = {https://dblp.org/rec/conf/icassp/ManguSKKS13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/SoltauKMSB13,
author = {Hagen Soltau and
Hong{-}Kwang Kuo and
Lidia Mangu and
George Saon and
Tom{\'{a}}s Beran},
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 = {Neural network acoustic models for the {DARPA} {RATS} program},
booktitle = {14th Annual Conference of the International Speech Communication Association,
{INTERSPEECH} 2013, Lyon, France, August 25-29, 2013},
pages = {3092--3096},
publisher = {{ISCA}},
year = {2013},
url = {https://doi.org/10.21437/Interspeech.2013-674},
doi = {10.21437/INTERSPEECH.2013-674},
timestamp = {Tue, 11 Jun 2024 16:45:43 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/SoltauKMSB13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/SaonTSGK13,
author = {George Saon and
Samuel Thomas and
Hagen Soltau and
Sriram Ganapathy and
Brian Kingsbury},
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 = {The {IBM} speech activity detection system for the {DARPA} {RATS}
program},
booktitle = {14th Annual Conference of the International Speech Communication Association,
{INTERSPEECH} 2013, Lyon, France, August 25-29, 2013},
pages = {3497--3501},
publisher = {{ISCA}},
year = {2013},
url = {https://doi.org/10.21437/Interspeech.2013-264},
doi = {10.21437/INTERSPEECH.2013-264},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/SaonTSGK13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/SainathKMDSSBAR13,
author = {Tara N. Sainath and
Brian Kingsbury and
Abdel{-}rahman Mohamed and
George E. Dahl and
George Saon and
Hagen Soltau and
Tom{\'{a}}s Beran and
Aleksandr Y. Aravkin and
Bhuvana Ramabhadran},
title = {Improvements to deep convolutional neural networks for {LVCSR}},
journal = {CoRR},
volume = {abs/1309.1501},
year = {2013},
url = {http://arxiv.org/abs/1309.1501},
eprinttype = {arXiv},
eprint = {1309.1501},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/SainathKMDSSBAR13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/speech/SaonS12,
author = {George Saon and
Hagen Soltau},
title = {Boosting systems for large vocabulary continuous speech recognition},
journal = {Speech Commun.},
volume = {54},
number = {2},
pages = {212--218},
year = {2012},
url = {https://doi.org/10.1016/j.specom.2011.07.011},
doi = {10.1016/J.SPECOM.2011.07.011},
timestamp = {Sat, 22 Feb 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/speech/SaonS12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/spm/SaonC12,
author = {George Saon and
Jen{-}Tzung Chien},
title = {Large-Vocabulary Continuous Speech Recognition Systems: {A} Look at
Some Recent Advances},
journal = {{IEEE} Signal Process. Mag.},
volume = {29},
number = {6},
pages = {18--33},
year = {2012},
url = {https://doi.org/10.1109/MSP.2012.2197156},
doi = {10.1109/MSP.2012.2197156},
timestamp = {Wed, 14 Jun 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/spm/SaonC12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/taslp/SaonC12,
author = {George Saon and
Jen{-}Tzung Chien},
title = {Bayesian Sensing Hidden Markov Models},
journal = {{IEEE} Trans. Speech Audio Process.},
volume = {20},
number = {1},
pages = {43--54},
year = {2012},
url = {https://doi.org/10.1109/TASL.2011.2129911},
doi = {10.1109/TASL.2011.2129911},
timestamp = {Sun, 17 May 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/taslp/SaonC12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/apsipa/SaonC12,
author = {George Saon and
Jen{-}Tzung Chien},
title = {Recent developments in large vocabulary continuous speech recognition},
booktitle = {Asia-Pacific Signal and Information Processing Association Annual
Summit and Conference, {APSIPA} 2012, Hollywood, CA, USA, December
3-6, 2012},
pages = {1--6},
publisher = {{IEEE}},
year = {2012},
url = {https://ieeexplore.ieee.org/document/6411850/},
timestamp = {Sun, 08 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/apsipa/SaonC12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/SaonK12,
author = {George Saon and
Brian Kingsbury},
title = {Discriminative feature-space transforms using deep neural networks},
booktitle = {13th Annual Conference of the International Speech Communication Association,
{INTERSPEECH} 2012, Portland, Oregon, USA, September 9-13, 2012},
pages = {14--17},
publisher = {{ISCA}},
year = {2012},
url = {https://doi.org/10.21437/Interspeech.2012-4},
doi = {10.21437/INTERSPEECH.2012-4},
timestamp = {Tue, 11 Jun 2024 16:45:43 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/SaonK12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/CuiASG12,
author = {Xiaodong Cui and
Mohamed Afify and
George Saon and
Vaibhava Goel},
title = {Sparse Bayesian Factor Analysis for Stereo-based Stochastic Mapping},
booktitle = {13th Annual Conference of the International Speech Communication Association,
{INTERSPEECH} 2012, Portland, Oregon, USA, September 9-13, 2012},
pages = {795--798},
publisher = {{ISCA}},
year = {2012},
url = {https://doi.org/10.21437/Interspeech.2012-243},
doi = {10.21437/INTERSPEECH.2012-243},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/CuiASG12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ibmrd/PichenyNGKRRS11,
author = {Michael Picheny and
David Nahamoo and
Vaibhava Goel and
Brian Kingsbury and
Bhuvana Ramabhadran and
Steven J. Rennie and
George Saon},
title = {Trends and advances in speech recognition},
journal = {{IBM} J. Res. Dev.},
volume = {55},
number = {5},
pages = {2},
year = {2011},
url = {https://doi.org/10.1147/JRD.2011.2163277},
doi = {10.1147/JRD.2011.2163277},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ibmrd/PichenyNGKRRS11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/asru/SaonC11,
author = {George Saon and
Jen{-}Tzung Chien},
editor = {David Nahamoo and
Michael Picheny},
title = {Some properties of Bayesian sensing hidden Markov models},
booktitle = {2011 {IEEE} Workshop on Automatic Speech Recognition {\&} Understanding,
{ASRU} 2011, Waikoloa, HI, USA, December 11-15, 2011},
pages = {65--70},
publisher = {{IEEE}},
year = {2011},
url = {https://doi.org/10.1109/ASRU.2011.6163907},
doi = {10.1109/ASRU.2011.6163907},
timestamp = {Wed, 16 Oct 2019 14:14:51 +0200},
biburl = {https://dblp.org/rec/conf/asru/SaonC11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/asru/KuoAMS11,
author = {Hong{-}Kwang Jeff Kuo and
Ebru Arisoy and
Lidia Mangu and
George Saon},
editor = {David Nahamoo and
Michael Picheny},
title = {Minimum Bayes risk discriminative language models for Arabic speech
recognition},
booktitle = {2011 {IEEE} Workshop on Automatic Speech Recognition {\&} Understanding,
{ASRU} 2011, Waikoloa, HI, USA, December 11-15, 2011},
pages = {208--213},
publisher = {{IEEE}},
year = {2011},
url = {https://doi.org/10.1109/ASRU.2011.6163932},
doi = {10.1109/ASRU.2011.6163932},
timestamp = {Fri, 26 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/asru/KuoAMS11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/asru/ManguKCKSSB11,
author = {Lidia Mangu and
Hong{-}Kwang Kuo and
Stephen M. Chu and
Brian Kingsbury and
George Saon and
Hagen Soltau and
Fadi Biadsy},
editor = {David Nahamoo and
Michael Picheny},
title = {The {IBM} 2011 {GALE} Arabic speech transcription system},
booktitle = {2011 {IEEE} Workshop on Automatic Speech Recognition {\&} Understanding,
{ASRU} 2011, Waikoloa, HI, USA, December 11-15, 2011},
pages = {272--277},
publisher = {{IEEE}},
year = {2011},
url = {https://doi.org/10.1109/ASRU.2011.6163943},
doi = {10.1109/ASRU.2011.6163943},
timestamp = {Fri, 26 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/asru/ManguKCKSSB11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/KingsburySSCKMRMJ11,
author = {Brian Kingsbury and
Hagen Soltau and
George Saon and
Stephen M. Chu and
Hong{-}Kwang Kuo and
Lidia Mangu and
Suman V. Ravuri and
Nelson Morgan and
Adam Janin},
title = {The {IBM} 2009 {GALE} Arabic speech transcription system},
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 = {4672--4675},
publisher = {{IEEE}},
year = {2011},
url = {https://doi.org/10.1109/ICASSP.2011.5947397},
doi = {10.1109/ICASSP.2011.5947397},
timestamp = {Fri, 19 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/KingsburySSCKMRMJ11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/SaonC11,
author = {George Saon and
Jen{-}Tzung Chien},
title = {Bayesian sensing hidden Markov models for 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 = {5056--5059},
publisher = {{IEEE}},
year = {2011},
url = {https://doi.org/10.1109/ICASSP.2011.5947493},
doi = {10.1109/ICASSP.2011.5947493},
timestamp = {Thu, 15 Jun 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/SaonC11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/SaonC11a,
author = {George Saon and
Jen{-}Tzung Chien},
title = {Discriminative training for Bayesian sensing hidden Markov models},
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 = {5316--5319},
publisher = {{IEEE}},
year = {2011},
url = {https://doi.org/10.1109/ICASSP.2011.5947558},
doi = {10.1109/ICASSP.2011.5947558},
timestamp = {Thu, 15 Jun 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/SaonC11a.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/mlslp/SaonC11,
author = {George Saon and
Jen{-}Tzung Chien},
title = {Bayesian sensing hidden Markov models for speech recognition},
booktitle = {2011 Symposium on Machine Learning in Speech and Language Processing,
{MLSLP} 2011, Bellevue, WA, USA, June 27, 2011},
publisher = {{ISCA}},
year = {2011},
url = {https://www.isca-archive.org/mlslp\_2011/saon11\_mlslp.html},
timestamp = {Thu, 01 Aug 2024 15:37:24 +0200},
biburl = {https://dblp.org/rec/conf/mlslp/SaonC11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/SaonSCCKKMP10,
author = {George Saon and
Hagen Soltau and
Upendra V. Chaudhari and
Stephen M. Chu and
Brian Kingsbury and
Hong{-}Kwang Kuo and
Lidia Mangu and
Daniel Povey},
title = {The {IBM} 2008 {GALE} Arabic speech transcription system},
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 = {4378--4381},
publisher = {{IEEE}},
year = {2010},
url = {https://doi.org/10.1109/ICASSP.2010.5495640},
doi = {10.1109/ICASSP.2010.5495640},
timestamp = {Fri, 19 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/SaonSCCKKMP10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/SaonS10,
author = {George Saon and
Hagen Soltau},
editor = {Takao Kobayashi and
Keikichi Hirose and
Satoshi Nakamura},
title = {Boosting systems for {LVCSR}},
booktitle = {11th Annual Conference of the International Speech Communication Association,
{INTERSPEECH} 2010, Makuhari, Chiba, Japan, September 26-30, 2010},
pages = {1341--1344},
publisher = {{ISCA}},
year = {2010},
url = {https://doi.org/10.21437/Interspeech.2010-16},
doi = {10.21437/INTERSPEECH.2010-16},
timestamp = {Tue, 11 Jun 2024 16:45:43 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/SaonS10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/slt/SoltauSK10,
author = {Hagen Soltau and
George Saon and
Brian Kingsbury},
editor = {Dilek Hakkani{-}T{\"{u}}r and
Mari Ostendorf},
title = {The {IBM} Attila speech recognition toolkit},
booktitle = {2010 {IEEE} Spoken Language Technology Workshop, {SLT} 2010, Berkeley,
California, USA, December 12-15, 2010},
pages = {97--102},
publisher = {{IEEE}},
year = {2010},
url = {https://doi.org/10.1109/SLT.2010.5700829},
doi = {10.1109/SLT.2010.5700829},
timestamp = {Wed, 16 Oct 2019 14:14:53 +0200},
biburl = {https://dblp.org/rec/conf/slt/SoltauSK10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/taslp/SoltauSKKMPE09,
author = {Hagen Soltau and
George Saon and
Brian Kingsbury and
Hong{-}Kwang Jeff Kuo and
Lidia Mangu and
Daniel Povey and
Ahmad Emami},
title = {Advances in Arabic Speech Transcription at {IBM} Under the {DARPA}
{GALE} Program},
journal = {{IEEE} Trans. Speech Audio Process.},
volume = {17},
number = {5},
pages = {884--894},
year = {2009},
url = {https://doi.org/10.1109/TASL.2009.2022966},
doi = {10.1109/TASL.2009.2022966},
timestamp = {Sun, 17 May 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/taslp/SoltauSKKMPE09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/asru/SoltauS09,
author = {Hagen Soltau and
George Saon},
title = {Dynamic network decoding revisited},
booktitle = {2009 {IEEE} Workshop on Automatic Speech Recognition {\&} Understanding,
{ASRU} 2009, Merano/Meran, Italy, December 13-17, 2009},
pages = {276--281},
publisher = {{IEEE}},
year = {2009},
url = {https://doi.org/10.1109/ASRU.2009.5372904},
doi = {10.1109/ASRU.2009.5372904},
timestamp = {Wed, 16 Oct 2019 14:14:51 +0200},
biburl = {https://dblp.org/rec/conf/asru/SoltauS09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/SaonPS09,
author = {George Saon and
Daniel Povey and
Hagen Soltau},
title = {Large margin semi-tied covariance transforms for discriminative training},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing, {ICASSP} 2009, 19-24 April 2009, Taipei, Taiwan},
pages = {3753--3756},
publisher = {{IEEE}},
year = {2009},
url = {https://doi.org/10.1109/ICASSP.2009.4960443},
doi = {10.1109/ICASSP.2009.4960443},
timestamp = {Thu, 23 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/SaonPS09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/PoveyKKRSV08,
author = {Daniel Povey and
Dimitri Kanevsky and
Brian Kingsbury and
Bhuvana Ramabhadran and
George Saon and
Karthik Visweswariah},
title = {Boosted {MMI} for model and feature-space discriminative training},
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 = {4057--4060},
publisher = {{IEEE}},
year = {2008},
url = {https://doi.org/10.1109/ICASSP.2008.4518545},
doi = {10.1109/ICASSP.2008.4518545},
timestamp = {Fri, 19 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/PoveyKKRSV08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/SaonP08,
author = {George Saon and
Daniel Povey},
title = {Penalty function maximization for large margin {HMM} training},
booktitle = {9th Annual Conference of the International Speech Communication Association,
{INTERSPEECH} 2008, Brisbane, Australia, September 22-26, 2008},
pages = {920--923},
publisher = {{ISCA}},
year = {2008},
url = {https://doi.org/10.21437/Interspeech.2008-108},
doi = {10.21437/INTERSPEECH.2008-108},
timestamp = {Tue, 11 Jun 2024 16:45:43 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/SaonP08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/asru/SaonP07,
author = {George Saon and
Michael Picheny},
editor = {Sadaoki Furui and
Tatsuya Kawahara},
title = {Lattice-based Viterbi decoding techniques for speech translation},
booktitle = {{IEEE} Workshop on Automatic Speech Recognition {\&} Understanding,
{ASRU} 2007, Kyoto, Japan, December 9-13, 2007},
pages = {386--389},
publisher = {{IEEE}},
year = {2007},
url = {https://doi.org/10.1109/ASRU.2007.4430143},
doi = {10.1109/ASRU.2007.4430143},
timestamp = {Wed, 16 Oct 2019 14:14:51 +0200},
biburl = {https://dblp.org/rec/conf/asru/SaonP07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/SoltauSKKMPZ07,
author = {Hagen Soltau and
George Saon and
Brian Kingsbury and
Hong{-}Kwang Jeff Kuo and
Lidia Mangu and
Daniel Povey and
Geoffrey Zweig},
title = {The {IBM} 2006 Gale Arabic {ASR} System},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing, {ICASSP} 2007, Honolulu, Hawaii, USA, April
15-20, 2007},
pages = {349--352},
publisher = {{IEEE}},
year = {2007},
url = {https://doi.org/10.1109/ICASSP.2007.366921},
doi = {10.1109/ICASSP.2007.366921},
timestamp = {Mon, 22 Jun 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/SoltauSKKMPZ07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/taslp/ChenKMPSSZ06,
author = {Stanley F. Chen and
Brian Kingsbury and
Lidia Mangu and
Daniel Povey and
George Saon and
Hagen Soltau and
Geoffrey Zweig},
title = {Advances in speech transcription at {IBM} under the {DARPA} {EARS}
program},
journal = {{IEEE} Trans. Speech Audio Process.},
volume = {14},
number = {5},
pages = {1596--1608},
year = {2006},
url = {https://doi.org/10.1109/TASL.2006.879814},
doi = {10.1109/TASL.2006.879814},
timestamp = {Sun, 17 May 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/taslp/ChenKMPSSZ06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/Saon06,
author = {George Saon},
title = {A Non-Linear Speaker Adaptation Technique using Kernel Ridge Regression},
booktitle = {2006 {IEEE} International Conference on Acoustics Speech and Signal
Processing, {ICASSP} 2006, Toulouse, France, May 14-19, 2006},
pages = {225--228},
publisher = {{IEEE}},
year = {2006},
url = {https://doi.org/10.1109/ICASSP.2006.1659998},
doi = {10.1109/ICASSP.2006.1659998},
timestamp = {Mon, 22 Jun 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/Saon06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/ZweigSSRPMK06,
author = {Geoffrey Zweig and
Olivier Siohan and
George Saon and
Bhuvana Ramabhadran and
Daniel Povey and
Lidia Mangu and
Brian Kingsbury},
title = {Automated Quality Monitoring in the Call Center with {ASR} and Maximum
Entropy},
booktitle = {2006 {IEEE} International Conference on Acoustics Speech and Signal
Processing, {ICASSP} 2006, Toulouse, France, May 14-19, 2006},
pages = {589--592},
publisher = {{IEEE}},
year = {2006},
url = {https://doi.org/10.1109/ICASSP.2006.1660089},
doi = {10.1109/ICASSP.2006.1660089},
timestamp = {Mon, 22 Jun 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/ZweigSSRPMK06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/PoveyS06,
author = {Daniel Povey and
George Saon},
title = {Feature and model space speaker adaptation with full covariance Gaussians},
booktitle = {Ninth International Conference on Spoken Language Processing, {INTERSPEECH-ICSLP}
2006, Pittsburgh, PA, USA, September 17-21, 2006},
publisher = {{ISCA}},
year = {2006},
url = {https://doi.org/10.21437/Interspeech.2006-349},
doi = {10.21437/INTERSPEECH.2006-349},
timestamp = {Tue, 11 Jun 2024 16:45:43 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/PoveyS06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/naacl/ZweigSSRPMK06,
author = {Geoffrey Zweig and
Olivier Siohan and
George Saon and
Bhuvana Ramabhadran and
Daniel Povey and
Lidia Mangu and
Brian Kingsbury},
editor = {Robert C. Moore and
Jeff A. Bilmes and
Jennifer Chu{-}Carroll and
Mark Sanderson},
title = {Automated Quality Monitoring for Call Centers using Speech and {NLP}
Technologies},
booktitle = {Human Language Technology Conference of the North American Chapter
of the Association of Computational Linguistics, Proceedings, June
4-9, 2006, New York, New York, {USA}},
publisher = {The Association for Computational Linguistics},
year = {2006},
url = {https://aclanthology.org/N06-4011/},
timestamp = {Fri, 06 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/naacl/ZweigSSRPMK06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/slt/SaonRZ06,
author = {George Saon and
Bhuvana Ramabhadran and
Geoffrey Zweig},
editor = {Mazin Gilbert and
Hermann Ney},
title = {On the Effect Ofword Error Rate on Automated Quality Monitoring},
booktitle = {2006 {IEEE} {ACL} Spoken Language Technology Workshop, {SLT} 2006,
Palm Beach, Aruba, December 10-13, 2006},
pages = {106--109},
publisher = {{IEEE}},
year = {2006},
url = {https://doi.org/10.1109/SLT.2006.326828},
doi = {10.1109/SLT.2006.326828},
timestamp = {Wed, 16 Oct 2019 14:14:53 +0200},
biburl = {https://dblp.org/rec/conf/slt/SaonRZ06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/SoltauKMPSZ05,
author = {Hagen Soltau and
Brian Kingsbury and
Lidia Mangu and
Daniel Povey and
George Saon and
Geoffrey Zweig},
title = {The {IBM} 2004 Conversational Telephony System for Rich Transcription},
booktitle = {2005 {IEEE} International Conference on Acoustics, Speech, and Signal
Processing, {ICASSP} '05, Philadelphia, Pennsylvania, USA, March 18-23,
2005},
pages = {205--208},
publisher = {{IEEE}},
year = {2005},
url = {https://doi.org/10.1109/ICASSP.2005.1415086},
doi = {10.1109/ICASSP.2005.1415086},
timestamp = {Mon, 22 Jun 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/SoltauKMPSZ05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/PoveyKMSSZ05,
author = {Daniel Povey and
Brian Kingsbury and
Lidia Mangu and
George Saon and
Hagen Soltau and
Geoffrey Zweig},
title = {fMPE: Discriminatively Trained Features for Speech Recognition},
booktitle = {2005 {IEEE} International Conference on Acoustics, Speech, and Signal
Processing, {ICASSP} '05, Philadelphia, Pennsylvania, USA, March 18-23,
2005},
pages = {961--964},
publisher = {{IEEE}},
year = {2005},
url = {https://doi.org/10.1109/ICASSP.2005.1415275},
doi = {10.1109/ICASSP.2005.1415275},
timestamp = {Mon, 22 Jun 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/PoveyKMSSZ05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/SaonPZ05,
author = {George Saon and
Daniel Povey and
Geoffrey Zweig},
title = {Anatomy of an extremely fast {LVCSR} decoder},
booktitle = {9th European Conference on Speech Communication and Technology, INTERSPEECH-Eurospeech
2005, Lisbon, Portugal, September 4-8, 2005},
pages = {549--552},
publisher = {{ISCA}},
year = {2005},
url = {https://doi.org/10.21437/Interspeech.2005-338},
doi = {10.21437/INTERSPEECH.2005-338},
timestamp = {Tue, 11 Jun 2024 16:45:43 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/SaonPZ05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/csl/YvonZS04,
author = {Fran{\c{c}}ois Yvon and
Geoffrey Zweig and
George Saon},
title = {Arc minimization in finite-state decoding graphs with cross-word acoustic
context},
journal = {Comput. Speech Lang.},
volume = {18},
number = {4},
pages = {397--415},
year = {2004},
url = {https://doi.org/10.1016/j.csl.2003.09.006},
doi = {10.1016/J.CSL.2003.09.006},
timestamp = {Thu, 20 Feb 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/csl/YvonZS04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/SarikayaGS04,
author = {Ruhi Sarikaya and
Yuqing Gao and
George Saon},
title = {Fractional Fourier transform features for speech recognition},
booktitle = {2004 {IEEE} International Conference on Acoustics, Speech, and Signal
Processing, {ICASSP} 2004, Montreal, Quebec, Canada, May 17-21, 2004},
pages = {52},
publisher = {{IEEE}},
year = {2004},
url = {https://doi.org/10.1109/ICASSP.2004.1326039},
doi = {10.1109/ICASSP.2004.1326039},
timestamp = {Mon, 22 Jun 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/SarikayaGS04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/SaonDP04,
author = {George Saon and
Satya Dharanipragada and
Daniel Povey},
title = {Feature space Gaussianization},
booktitle = {2004 {IEEE} International Conference on Acoustics, Speech, and Signal
Processing, {ICASSP} 2004, Montreal, Quebec, Canada, May 17-21, 2004},
pages = {329--332},
publisher = {{IEEE}},
year = {2004},
url = {https://doi.org/10.1109/ICASSP.2004.1325989},
doi = {10.1109/ICASSP.2004.1325989},
timestamp = {Mon, 28 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/SaonDP04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/KingsburyMSZAGVP03,
author = {Brian Kingsbury and
Lidia Mangu and
George Saon and
Geoffrey Zweig and
Scott Axelrod and
Vaibhava Goel and
Karthik Visweswariah and
Michael Picheny},
title = {Toward domain-independent conversational speech recognition},
booktitle = {8th European Conference on Speech Communication and Technology, {EUROSPEECH}
2003 - {INTERSPEECH} 2003, Geneva, Switzerland, September 1-4, 2003},
pages = {1881--1884},
publisher = {{ISCA}},
year = {2003},
url = {https://doi.org/10.21437/Eurospeech.2003-566},
doi = {10.21437/EUROSPEECH.2003-566},
timestamp = {Thu, 22 Jun 2023 16:42:17 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/KingsburyMSZAGVP03.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/SaonZKMC03,
author = {George Saon and
Geoffrey Zweig and
Brian Kingsbury and
Lidia Mangu and
Upendra V. Chaudhari},
title = {An architecture for rapid decoding of large vocabulary conversational
speech},
booktitle = {8th European Conference on Speech Communication and Technology, {EUROSPEECH}
2003 - {INTERSPEECH} 2003, Geneva, Switzerland, September 1-4, 2003},
pages = {1977--1980},
publisher = {{ISCA}},
year = {2003},
url = {https://doi.org/10.21437/Eurospeech.2003-571},
doi = {10.21437/EUROSPEECH.2003-571},
timestamp = {Thu, 22 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/SaonZKMC03.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/taslp/PadmanabhanSHKM02,
author = {Mukund Padmanabhan and
George Saon and
Jing Huang and
Brian Kingsbury and
Lidia Mangu},
title = {Automatic speech recognition performance on a voicemail transcription
task},
journal = {{IEEE} Trans. Speech Audio Process.},
volume = {10},
number = {7},
pages = {433--442},
year = {2002},
url = {https://doi.org/10.1109/TSA.2002.804303},
doi = {10.1109/TSA.2002.804303},
timestamp = {Sun, 17 May 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/taslp/PadmanabhanSHKM02.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/FineSG02,
author = {Shai Fine and
George Saon and
Ramesh A. Gopinath},
title = {Digit recognition in noisy environments via a sequential {GMM/SVM}
system},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing, {ICASSP} 2002, May 13-17 2002, Orlando, Florida,
{USA}},
pages = {49--52},
publisher = {{IEEE}},
year = {2002},
url = {https://doi.org/10.1109/ICASSP.2002.5743651},
doi = {10.1109/ICASSP.2002.5743651},
timestamp = {Wed, 16 Oct 2019 14:14:52 +0200},
biburl = {https://dblp.org/rec/conf/icassp/FineSG02.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/KingsburySMPS02,
author = {Brian Kingsbury and
George Saon and
Lidia Mangu and
Mukund Padmanabhan and
Ruhi Sarikaya},
title = {Robust speech recognition in Noisy Environments: The 2001 {IBM} spine
evaluation system},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing, {ICASSP} 2002, May 13-17 2002, Orlando, Florida,
{USA}},
pages = {53--56},
publisher = {{IEEE}},
year = {2002},
url = {https://doi.org/10.1109/ICASSP.2002.5743652},
doi = {10.1109/ICASSP.2002.5743652},
timestamp = {Fri, 19 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/KingsburySMPS02.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/ZweigSY02,
author = {Geoffrey Zweig and
George Saon and
Fran{\c{c}}ois Yvon},
editor = {John H. L. Hansen and
Bryan L. Pellom},
title = {Arc minimization in finite state decoding graphs with cross-word acoustic
context},
booktitle = {7th International Conference on Spoken Language Processing, {ICSLP2002}
- {INTERSPEECH} 2002, Denver, Colorado, USA, September 16-20, 2002},
pages = {389--392},
publisher = {{ISCA}},
year = {2002},
url = {https://doi.org/10.21437/ICSLP.2002-162},
doi = {10.21437/ICSLP.2002-162},
timestamp = {Thu, 22 Jun 2023 16:42:18 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/ZweigSY02.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/SaonH02,
author = {George Saon and
Juan M. Huerta},
editor = {John H. L. Hansen and
Bryan L. Pellom},
title = {Improvements to the {IBM} Aurora 2 multi-condition system},
booktitle = {7th International Conference on Spoken Language Processing, {ICSLP2002}
- {INTERSPEECH} 2002, Denver, Colorado, USA, September 16-20, 2002},
pages = {469--472},
publisher = {{ISCA}},
year = {2002},
url = {https://doi.org/10.21437/ICSLP.2002-21},
doi = {10.21437/ICSLP.2002-21},
timestamp = {Thu, 22 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/SaonH02.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/taslp/SaonP01,
author = {George Saon and
Mukund Padmanabhan},
title = {Data-driven approach to designing compound words for continuous speech
recognition},
journal = {{IEEE} Trans. Speech Audio Process.},
volume = {9},
number = {4},
pages = {327--332},
year = {2001},
url = {https://doi.org/10.1109/89.917678},
doi = {10.1109/89.917678},
timestamp = {Sun, 17 May 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/taslp/SaonP01.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/SaonZP01,
author = {George Saon and
Geoffrey Zweig and
Mukund Padmanabhan},
title = {Linear feature space projections for speaker adaptation},
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 = {325--328},
publisher = {{IEEE}},
year = {2001},
url = {https://doi.org/10.1109/ICASSP.2001.940833},
doi = {10.1109/ICASSP.2001.940833},
timestamp = {Thu, 23 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/SaonZP01.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/AaronCCDEFLLMMMNOPPRSSTVY01,
author = {Andrew Aaron and
Scott Saobing Chen and
Paul S. Cohen and
Satya Dharanipragada and
Ellen Eide and
Martin Franz and
Jean{-}Michel LeRoux and
X. Luo and
Beno{\^{\i}}t Maison and
Lidia Mangu and
T. Mathes and
Miroslav Novak and
Peder A. Olsen and
Michael Picheny and
Harry Printz and
Bhuvana Ramabhadran and
Andrej Sakrajda and
George Saon and
Borivoj Tydlit{\'{a}}t and
Karthik Visweswariah and
D. Yuk},
title = {Speech recognition for {DARPA} Communicator},
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 = {489--492},
publisher = {{IEEE}},
year = {2001},
url = {https://doi.org/10.1109/ICASSP.2001.940874},
doi = {10.1109/ICASSP.2001.940874},
timestamp = {Thu, 23 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/AaronCCDEFLLMMMNOPPRSSTVY01.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/SaonHJ01,
author = {George Saon and
Juan M. Huerta and
Ea{-}Ee Jan},
editor = {Paul Dalsgaard and
B{\o}rge Lindberg and
Henrik Benner and
Zheng{-}Hua Tan},
title = {Robust digit recognition in noisy environments: the {IBM} Aurora 2
system},
booktitle = {{EUROSPEECH} 2001 Scandinavia, 7th European Conference on Speech Communication
and Technology, 2nd {INTERSPEECH} Event, Aalborg, Denmark, September
3-7, 2001},
pages = {629--632},
publisher = {{ISCA}},
year = {2001},
url = {https://doi.org/10.21437/Eurospeech.2001-166},
doi = {10.21437/EUROSPEECH.2001-166},
timestamp = {Thu, 22 Jun 2023 16:42:18 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/SaonHJ01.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/SaonPGC00,
author = {George Saon and
Mukund Padmanabhan and
Ramesh A. Gopinath and
Scott Saobing Chen},
title = {Maximum likelihood discriminant feature spaces},
booktitle = {{IEEE} International Conference on Acoustics, Speech, and Signal Processing.
{ICASSP} 2000, 5-9 June, 2000, Hilton Hotel and Convention Center,
Istanbul, Turkey},
pages = {1129--1132},
publisher = {{IEEE}},
year = {2000},
url = {https://doi.org/10.1109/ICASSP.2000.859163},
doi = {10.1109/ICASSP.2000.859163},
timestamp = {Thu, 23 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/SaonPGC00.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/SaonP00,
author = {George Saon and
Mukund Padmanabhan},
title = {Minimum Bayes error feature selection},
booktitle = {Sixth International Conference on Spoken Language Processing, {ICSLP}
2000 / {INTERSPEECH} 2000, Beijing, China, October 16-20, 2000},
pages = {75--78},
publisher = {{ISCA}},
year = {2000},
url = {https://doi.org/10.21437/ICSLP.2000-481},
doi = {10.21437/ICSLP.2000-481},
timestamp = {Thu, 22 Jun 2023 16:42:19 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/SaonP00.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/HuangKMPSZ00,
author = {Jing Huang and
Brian Kingsbury and
Lidia Mangu and
Mukund Padmanabhan and
George Saon and
Geoffrey Zweig},
title = {Recent improvements in speech recognition performance on large vocabulary
conversational speech (voicemail and switchboard)},
booktitle = {Sixth International Conference on Spoken Language Processing, {ICSLP}
2000 / {INTERSPEECH} 2000, Beijing, China, October 16-20, 2000},
pages = {338--341},
publisher = {{ISCA}},
year = {2000},
url = {https://doi.org/10.21437/ICSLP.2000-819},
doi = {10.21437/ICSLP.2000-819},
timestamp = {Thu, 22 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/HuangKMPSZ00.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/JanOSR00,
author = {Ea{-}Ee Jan and
Jaime Botella Ordinas and
George Saon and
Salim Roukos},
title = {Real-time multilingual {HMM} training robust to channel variations},
booktitle = {Sixth International Conference on Spoken Language Processing, {ICSLP}
2000 / {INTERSPEECH} 2000, Beijing, China, October 16-20, 2000},
pages = {925--928},
publisher = {{ISCA}},
year = {2000},
url = {https://doi.org/10.21437/ICSLP.2000-685},
doi = {10.21437/ICSLP.2000-685},
timestamp = {Thu, 22 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/JanOSR00.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/SaonP00,
author = {George Saon and
Mukund Padmanabhan},
editor = {Todd K. Leen and
Thomas G. Dietterich and
Volker Tresp},
title = {Minimum Bayes Error Feature Selection for Continuous Speech Recognition},
booktitle = {Advances in Neural Information Processing Systems 13, Papers from
Neural Information Processing Systems {(NIPS)} 2000, Denver, CO, {USA}},
pages = {800--806},
publisher = {{MIT} Press},
year = {2000},
url = {https://proceedings.neurips.cc/paper/2000/hash/59e0b2658e9f2e77f8d4d83f8d07ca84-Abstract.html},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/SaonP00.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ijdar/Saon99,
author = {George Saon},
title = {Cursive word recognition using a random field based hidden Markov
model},
journal = {Int. J. Document Anal. Recognit.},
volume = {1},
number = {4},
pages = {199--208},
year = {1999},
url = {https://doi.org/10.1007/s100320050019},
doi = {10.1007/S100320050019},
timestamp = {Thu, 13 Aug 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ijdar/Saon99.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/PadmanabhanSBHZ99,
author = {Mukund Padmanabhan and
George Saon and
Sankar Basu and
Jing Huang and
Geoffrey Zweig},
title = {Recent improvements in voicemail transcription},
booktitle = {Sixth European Conference on Speech Communication and Technology,
{EUROSPEECH} 1999, Budapest, Hungary, September 5-9, 1999},
pages = {503--506},
publisher = {{ISCA}},
year = {1999},
url = {https://doi.org/10.21437/Eurospeech.1999-129},
doi = {10.21437/EUROSPEECH.1999-129},
timestamp = {Wed, 18 Sep 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/PadmanabhanSBHZ99.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@phdthesis{DBLP:phd/hal/Saon97,
author = {George Saon},
title = {Mod{\`{e}}les markoviens uni- et bidimensionnels pour la reconnaissance
de l'{\'{e}}criture manuscrite hors-ligne. (One and two-dimensional
Markov models for off-line handwriting recognition)},
school = {Henri Poincar{\'{e}} University, Nancy, France},
year = {1997},
url = {https://hal.archives-ouvertes.fr/tel-01747325},
timestamp = {Thu, 12 May 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/phd/hal/Saon97.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ijprai/SaonB97,
author = {George Saon and
Abdel Bela{\"{\i}}d},
title = {High Performance Unconstrained Word Recognition System Combining HMMs
and Markov Random Fields},
journal = {Int. J. Pattern Recognit. Artif. Intell.},
volume = {11},
number = {5},
pages = {771--788},
year = {1997},
url = {https://doi.org/10.1142/S0218001497000342},
doi = {10.1142/S0218001497000342},
timestamp = {Mon, 11 May 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ijprai/SaonB97.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/SaonB97,
author = {George Saon and
Abdel Bela{\"{\i}}d},
title = {Binary pattern recognition using Markov random fields and HMMs},
booktitle = {1997 {IEEE} International Conference on Acoustics, Speech, and Signal
Processing, {ICASSP} '97, Munich, Germany, April 21-24, 1997},
pages = {3725--3728},
publisher = {{IEEE} Computer Society},
year = {1997},
url = {https://doi.org/10.1109/ICASSP.1997.604678},
doi = {10.1109/ICASSP.1997.604678},
timestamp = {Thu, 23 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/SaonB97.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icdar/SaonBG95,
author = {George Saon and
Abdel Bela{\"{\i}}d and
Yifan Gong},
title = {Stochastic trajectory modeling for recognition of unconstrained handwritten
words},
booktitle = {Third International Conference on Document Analysis and Recognition,
{ICDAR} 1995, August 14 - 15, 1995, Montreal, Canada. Volume {I}},
pages = {508--511},
publisher = {{IEEE} Computer Society},
year = {1995},
url = {https://doi.org/10.1109/ICDAR.1995.599045},
doi = {10.1109/ICDAR.1995.599045},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icdar/SaonBG95.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/mva/SaonBG94,
author = {George Saon and
Abdel Bela{\"{\i}}d and
Yifan Gong},
title = {Off-line Handwriting Recognition by Statistical Correlation},
booktitle = {Proceedings of {IAPR} Workshop on Machine Vision Applications, {MVA}
1994, December 13-15, 1994, Kawasaki, Japan},
pages = {371--374},
year = {1994},
url = {http://b2.cvl.iis.u-tokyo.ac.jp/mva/proceedings/CommemorativeDVD/1994/papers/1994371.pdf},
timestamp = {Wed, 19 May 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/mva/SaonBG94.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
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 2024-09-19 00:33 CEST 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:
