Stop the war!
Остановите войну!
for scientists:
default search action
BibTeX records: Roger Hsiao
@inproceedings{DBLP:conf/icassp/BraunMH23, author = {Stefan Braun and Erik McDermott and Roger Hsiao}, title = {Neural Transducer Training: Reduced Memory Consumption with Sample-Wise Computation}, 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/ICASSP49357.2023.10095544}, doi = {10.1109/ICASSP49357.2023.10095544}, timestamp = {Sun, 05 Nov 2023 16:51:21 +0100}, biburl = {https://dblp.org/rec/conf/icassp/BraunMH23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/SwietojanskiBCSGHHMMSTZ23, author = {Pawel Swietojanski and Stefan Braun and Dogan Can and Thiago Fraga da Silva and Arnab Ghoshal and Takaaki Hori and Roger Hsiao and Henry Mason and Erik McDermott and Honza Silovsky and Ruchir Travadi and Xiaodan Zhuang}, title = {Variable Attention Masking for Configurable Transformer Transducer 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/ICASSP49357.2023.10094588}, doi = {10.1109/ICASSP49357.2023.10094588}, timestamp = {Sun, 05 Nov 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/SwietojanskiBCSGHHMMSTZ23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2305-13652, author = {Jan Silovsk{\'{y}} and Liuhui Deng and Arturo Argueta and Tresi Arvizo and Roger Hsiao and Sasha Kuznietsov and Yiu{-}Chang Lin and Xiaoqiang Xiao and Yuanyuan Zhang}, title = {Cross-lingual Knowledge Transfer and Iterative Pseudo-labeling for Low-Resource Speech Recognition with Transducers}, journal = {CoRR}, volume = {abs/2305.13652}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2305.13652}, doi = {10.48550/ARXIV.2305.13652}, eprinttype = {arXiv}, eprint = {2305.13652}, timestamp = {Mon, 05 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2305-13652.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/sigmobile/LeeHCHYSECLLJMS22, author = {Inhee Lee and Roger Hsiao and Gordy Carichner and Chin{-}Wei Hsu and Mingyu Yang and Sara Shoouri and Katherine Ernst and Tess Carichner and Yuyang Li and Jaechan Lim and Cole R. Julick and Eunseong Moon and Yi Sun and Jamie Phillips and Kristi L. Montooth and Delbert A. Green II and Hun{-}Seok Kim and David T. Blaauw}, title = {Tracking the Migration of the Monarch Butterflies with the World's Smallest Computer}, journal = {GetMobile Mob. Comput. Commun.}, volume = {26}, number = {1}, pages = {25--29}, year = {2022}, url = {https://doi.org/10.1145/3539668.3539677}, doi = {10.1145/3539668.3539677}, timestamp = {Wed, 13 Mar 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/sigmobile/LeeHCHYSECLLJMS22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/DengHG22, author = {Liuhui Deng and Roger Hsiao and Arnab Ghoshal}, title = {Bilingual End-to-End {ASR} with Byte-Level Subwords}, booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2022, Virtual and Singapore, 23-27 May 2022}, pages = {6417--6421}, publisher = {{IEEE}}, year = {2022}, url = {https://doi.org/10.1109/ICASSP43922.2022.9747842}, doi = {10.1109/ICASSP43922.2022.9747842}, timestamp = {Tue, 07 Jun 2022 17:34:47 +0200}, biburl = {https://dblp.org/rec/conf/icassp/DengHG22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2205-00485, author = {Liuhui Deng and Roger Hsiao and Arnab Ghoshal}, title = {Bilingual End-to-End {ASR} with Byte-Level Subwords}, journal = {CoRR}, volume = {abs/2205.00485}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2205.00485}, doi = {10.48550/ARXIV.2205.00485}, eprinttype = {arXiv}, eprint = {2205.00485}, timestamp = {Tue, 03 May 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2205-00485.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2210-12214, author = {Thien Nguyen and Nathalie Tran and Liuhui Deng and Thiago Fraga da Silva and Matthew Radzihovsky and Roger Hsiao and Henry Mason and Stefan Braun and Erik McDermott and Dogan Can and Pawel Swietojanski and Lyan Verwimp and Sibel Oyman and Tresi Arvizo and Honza Silovsky and Arnab Ghoshal and Mathieu Martel and Bharat Ram Ambati and Mohamed Ali}, title = {Optimizing Bilingual Neural Transducer with Synthetic Code-switching Text Generation}, journal = {CoRR}, volume = {abs/2210.12214}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2210.12214}, doi = {10.48550/ARXIV.2210.12214}, eprinttype = {arXiv}, eprint = {2210.12214}, timestamp = {Fri, 28 Oct 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2210-12214.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2211-01438, author = {Pawel Swietojanski and Stefan Braun and Dogan Can and Thiago Fraga da Silva and Arnab Ghoshal and Takaaki Hori and Roger Hsiao and Henry Mason and Erik McDermott and Honza Silovsky and Ruchir Travadi and Xiaodan Zhuang}, title = {Variable Attention Masking for Configurable Transformer Transducer Speech Recognition}, journal = {CoRR}, volume = {abs/2211.01438}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2211.01438}, doi = {10.48550/ARXIV.2211.01438}, eprinttype = {arXiv}, eprint = {2211.01438}, timestamp = {Fri, 04 Nov 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2211-01438.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2211-16270, author = {Stefan Braun and Erik McDermott and Roger Hsiao}, title = {Neural Transducer Training: Reduced Memory Consumption with Sample-wise Computation}, journal = {CoRR}, volume = {abs/2211.16270}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2211.16270}, doi = {10.48550/ARXIV.2211.16270}, eprinttype = {arXiv}, eprint = {2211.16270}, timestamp = {Fri, 02 Dec 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2211-16270.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/mobicom/LeeHCHYSECLLJMS21, author = {Inhee Lee and Roger Hsiao and Gordy Carichner and Chin{-}Wei Hsu and Mingyu Yang and Sara Shoouri and Katherine Ernst and Tess Carichner and Yuyang Li and Jaechan Lim and Cole R. Julick and Eunseong Moon and Yi Sun and Jamie Phillips and Kristi L. Montooth and Delbert A. Green II and Hun{-}Seok Kim and David T. Blaauw}, title = {mSAIL: milligram-scale multi-modal sensor platform for monarch butterfly migration tracking}, booktitle = {{ACM} MobiCom '21: The 27th Annual International Conference on Mobile Computing and Networking, New Orleans, Louisiana, USA, October 25-29, 2021}, pages = {517--530}, publisher = {{ACM}}, year = {2021}, url = {https://doi.org/10.1145/3447993.3483263}, doi = {10.1145/3447993.3483263}, timestamp = {Wed, 13 Mar 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/mobicom/LeeHCHYSECLLJMS21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/spl/HsiaoCNTG20, author = {Roger Hsiao and Dogan Can and Tim Ng and Ruchir Travadi and Arnab Ghoshal}, title = {Online Automatic Speech Recognition With Listen, Attend and Spell Model}, journal = {{IEEE} Signal Process. Lett.}, volume = {27}, pages = {1889--1893}, year = {2020}, url = {https://doi.org/10.1109/LSP.2020.3031480}, doi = {10.1109/LSP.2020.3031480}, timestamp = {Thu, 17 Dec 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/spl/HsiaoCNTG20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/eusipco/YangHCELGLBK20, author = {Mingyu Yang and Roger Hsiao and Gordy Carichner and Katherine Ernst and Jaechan Lim and Delbert A. Green II and Inhee Lee and David T. Blaauw and Hun{-}Seok Kim}, title = {Migrating Monarch Butterfly Localization Using Multi-Modal Sensor Fusion Neural Networks}, booktitle = {28th European Signal Processing Conference, {EUSIPCO} 2020, Amsterdam, Netherlands, January 18-21, 2021}, pages = {1792--1796}, publisher = {{IEEE}}, year = {2020}, url = {https://doi.org/10.23919/Eusipco47968.2020.9287842}, doi = {10.23919/EUSIPCO47968.2020.9287842}, timestamp = {Wed, 07 Dec 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/eusipco/YangHCELGLBK20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/TitusSCHYG20, author = {Andrew Titus and Jan Silovsk{\'{y}} and Nanxin Chen and Roger Hsiao and Mary Young and Arnab Ghoshal}, title = {Improving Language Identification for Multilingual Speakers}, booktitle = {2020 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2020, Barcelona, Spain, May 4-8, 2020}, pages = {8284--8288}, publisher = {{IEEE}}, year = {2020}, url = {https://doi.org/10.1109/ICASSP40776.2020.9053057}, doi = {10.1109/ICASSP40776.2020.9053057}, timestamp = {Thu, 23 Jul 2020 16:19:28 +0200}, biburl = {https://dblp.org/rec/conf/icassp/TitusSCHYG20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2001-11019, author = {Andrew Titus and Jan Silovsk{\'{y}} and Nanxin Chen and Roger Hsiao and Mary Young and Arnab Ghoshal}, title = {Improving Language Identification for Multilingual Speakers}, journal = {CoRR}, volume = {abs/2001.11019}, year = {2020}, url = {https://arxiv.org/abs/2001.11019}, eprinttype = {arXiv}, eprint = {2001.11019}, timestamp = {Thu, 30 Jan 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2001-11019.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2008-05514, author = {Roger Hsiao and Dogan Can and Tim Ng and Ruchir Travadi and Arnab Ghoshal}, title = {Online Automatic Speech Recognition with Listen, Attend and Spell Model}, journal = {CoRR}, volume = {abs/2008.05514}, year = {2020}, url = {https://arxiv.org/abs/2008.05514}, eprinttype = {arXiv}, eprint = {2008.05514}, timestamp = {Mon, 17 Aug 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2008-05514.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1912-06907, author = {Mingyu Yang and Roger Hsiao and Gordy Carichner and Katherine Ernst and Jaechan Lim and Delbert A. Green II and Inhee Lee and David T. Blaauw and Hun{-}Seok Kim}, title = {Migrating Monarch Butterfly Localization Using Multi-Sensor Fusion Neural Networks}, journal = {CoRR}, volume = {abs/1912.06907}, year = {2019}, url = {http://arxiv.org/abs/1912.06907}, eprinttype = {arXiv}, eprint = {1912.06907}, timestamp = {Tue, 07 Jan 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-1912-06907.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/HsiaoNS17, author = {Roger Hsiao and Tim Ng and Man{-}Hung Siu}, title = {Unsupervised adaptation for deep neural networks using Alternating Direction Method of Multipliers}, booktitle = {2017 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2017, New Orleans, LA, USA, March 5-9, 2017}, pages = {5180--5184}, publisher = {{IEEE}}, year = {2017}, url = {https://doi.org/10.1109/ICASSP.2017.7953144}, doi = {10.1109/ICASSP.2017.7953144}, timestamp = {Wed, 16 Oct 2019 14:14:52 +0200}, biburl = {https://dblp.org/rec/conf/icassp/HsiaoNS17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/HartmannHT17, author = {William Hartmann and Roger Hsiao and Stavros Tsakalidis}, title = {Alternative networks for monolingual bottleneck features}, booktitle = {2017 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2017, New Orleans, LA, USA, March 5-9, 2017}, pages = {5290--5294}, publisher = {{IEEE}}, year = {2017}, url = {https://doi.org/10.1109/ICASSP.2017.7953166}, doi = {10.1109/ICASSP.2017.7953166}, timestamp = {Fri, 23 Jun 2017 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/HartmannHT17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/AlumaeKHHZNTS17, author = {Tanel Alum{\"{a}}e and Damianos G. Karakos and William Hartmann and Roger Hsiao and Le Zhang and Long Nguyen and Stavros Tsakalidis and Richard M. Schwartz}, title = {The 2016 {BBN} Georgian telephone speech keyword spotting system}, booktitle = {2017 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2017, New Orleans, LA, USA, March 5-9, 2017}, pages = {5755--5759}, publisher = {{IEEE}}, year = {2017}, url = {https://doi.org/10.1109/ICASSP.2017.7953259}, doi = {10.1109/ICASSP.2017.7953259}, timestamp = {Sun, 22 Mar 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/AlumaeKHHZNTS17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/HartmannKHZATS17, author = {William Hartmann and Damianos G. Karakos and Roger Hsiao and Le Zhang and Tanel Alum{\"{a}}e and Stavros Tsakalidis and Richard M. Schwartz}, title = {Analysis of keyword spotting performance across {IARPA} babel languages}, booktitle = {2017 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2017, New Orleans, LA, USA, March 5-9, 2017}, pages = {5765--5769}, publisher = {{IEEE}}, year = {2017}, url = {https://doi.org/10.1109/ICASSP.2017.7953261}, doi = {10.1109/ICASSP.2017.7953261}, timestamp = {Sun, 22 Mar 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/HartmannKHZATS17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/HartmannHNMKS17, author = {William Hartmann and Roger Hsiao and Tim Ng and Jeff Z. Ma and Francis Keith and Man{-}Hung Siu}, editor = {Francisco Lacerda}, title = {Improved Single System Conversational Telephone Speech Recognition with {VGG} Bottleneck Features}, booktitle = {Interspeech 2017, 18th Annual Conference of the International Speech Communication Association, Stockholm, Sweden, August 20-24, 2017}, pages = {112--116}, publisher = {{ISCA}}, year = {2017}, url = {https://doi.org/10.21437/Interspeech.2017-1513}, doi = {10.21437/INTERSPEECH.2017-1513}, timestamp = {Mon, 26 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/HartmannHNMKS17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/HartmannZBHTS16, author = {William Hartmann and Le Zhang and Kerri Barnes and Roger Hsiao and Stavros Tsakalidis and Richard M. Schwartz}, editor = {Nelson Morgan}, title = {Comparison of Multiple System Combination Techniques for Keyword Spotting}, booktitle = {Interspeech 2016, 17th Annual Conference of the International Speech Communication Association, San Francisco, CA, USA, September 8-12, 2016}, pages = {1913--1917}, publisher = {{ISCA}}, year = {2016}, url = {https://doi.org/10.21437/Interspeech.2016-1381}, doi = {10.21437/INTERSPEECH.2016-1381}, timestamp = {Mon, 26 Jun 2023 16:43:56 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/HartmannZBHTS16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/HartmannNHTS16, author = {William Hartmann and Tim Ng and Roger Hsiao and Stavros Tsakalidis and Richard M. Schwartz}, editor = {Nelson Morgan}, title = {Two-Stage Data Augmentation for Low-Resourced Speech Recognition}, booktitle = {Interspeech 2016, 17th Annual Conference of the International Speech Communication Association, San Francisco, CA, USA, September 8-12, 2016}, pages = {2378--2382}, publisher = {{ISCA}}, year = {2016}, url = {https://doi.org/10.21437/Interspeech.2016-1386}, doi = {10.21437/INTERSPEECH.2016-1386}, timestamp = {Fri, 29 Jan 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/interspeech/HartmannNHTS16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/HsiaoMNHJKASHKL16, author = {Roger Hsiao and Ralf Meermeier and Tim Ng and Zhongqiang Huang and Maxwell Jordan and Enoch Kan and Tanel Alum{\"{a}}e and Jan Silovsk{\'{y}} and William Hartmann and Francis Keith and Omer Lang and Man{-}Hung Siu and Owen Kimball}, editor = {Nelson Morgan}, title = {Sage: The New {BBN} Speech Processing Platform}, booktitle = {Interspeech 2016, 17th Annual Conference of the International Speech Communication Association, San Francisco, CA, USA, September 8-12, 2016}, pages = {3022--3026}, publisher = {{ISCA}}, year = {2016}, url = {https://doi.org/10.21437/Interspeech.2016-1031}, doi = {10.21437/INTERSPEECH.2016-1031}, timestamp = {Fri, 29 Jan 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/interspeech/HsiaoMNHJKASHKL16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/asru/HsiaoMHKGBSCWCM15, author = {Roger Hsiao and Jeff Z. Ma and William Hartmann and Martin Karafi{\'{a}}t and Frantisek Gr{\'{e}}zl and Luk{\'{a}}s Burget and Igor Sz{\"{o}}ke and Jan Cernock{\'{y}} and Shinji Watanabe and Zhuo Chen and Sri Harish Reddy Mallidi and Hynek Hermansky and Stavros Tsakalidis and Richard M. Schwartz}, title = {Robust speech recognition in unknown reverberant and noisy conditions}, booktitle = {2015 {IEEE} Workshop on Automatic Speech Recognition and Understanding, {ASRU} 2015, Scottsdale, AZ, USA, December 13-17, 2015}, pages = {533--538}, publisher = {{IEEE}}, year = {2015}, url = {https://doi.org/10.1109/ASRU.2015.7404841}, doi = {10.1109/ASRU.2015.7404841}, timestamp = {Thu, 14 Oct 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/asru/HsiaoMHKGBSCWCM15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/ZhangKHHST15, author = {Le Zhang and Damianos G. Karakos and William Hartmann and Roger Hsiao and Richard M. Schwartz and Stavros Tsakalidis}, title = {Enhancing low resource keyword spotting with automatically retrieved web documents}, booktitle = {{INTERSPEECH} 2015, 16th Annual Conference of the International Speech Communication Association, Dresden, Germany, September 6-10, 2015}, pages = {839--843}, publisher = {{ISCA}}, year = {2015}, url = {https://doi.org/10.21437/Interspeech.2015-262}, doi = {10.21437/INTERSPEECH.2015-262}, timestamp = {Fri, 23 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/ZhangKHHST15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/HsiaoNTNS15, author = {Roger Hsiao and Tim Ng and Stavros Tsakalidis and Long Nguyen and Richard M. Schwartz}, title = {Unsupervised adaptation for deep neural network using linear least square method}, booktitle = {{INTERSPEECH} 2015, 16th Annual Conference of the International Speech Communication Association, Dresden, Germany, September 6-10, 2015}, pages = {2887--2891}, publisher = {{ISCA}}, year = {2015}, url = {https://doi.org/10.21437/Interspeech.2015-607}, doi = {10.21437/INTERSPEECH.2015-607}, timestamp = {Fri, 23 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/HsiaoNTNS15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/TsakalidisHKNRSZNSM14, author = {Stavros Tsakalidis and Roger Hsiao and Damianos G. Karakos and Tim Ng and Shivesh Ranjan and Guruprasad Saikumar and Le Zhang and Long Nguyen and Richard M. Schwartz and John Makhoul}, title = {The 2013 {BBN} Vietnamese telephone speech keyword spotting system}, booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2014, Florence, Italy, May 4-9, 2014}, pages = {7829--7833}, publisher = {{IEEE}}, year = {2014}, url = {https://doi.org/10.1109/ICASSP.2014.6855124}, doi = {10.1109/ICASSP.2014.6855124}, timestamp = {Sun, 22 Mar 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/TsakalidisHKNRSZNSM14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/NgHZKMKVSZNS14, author = {Tim Ng and Roger Hsiao and Le Zhang and Damianos G. Karakos and Sri Harish Reddy Mallidi and Martin Karafi{\'{a}}t and Karel Vesel{\'{y}} and Igor Sz{\"{o}}ke and Bing Zhang and Long Nguyen and Richard M. Schwartz}, editor = {Haizhou Li and Helen M. Meng and Bin Ma and Engsiong Chng and Lei Xie}, title = {Progress in the {BBN} keyword search system for the {DARPA} {RATS} program}, booktitle = {{INTERSPEECH} 2014, 15th Annual Conference of the International Speech Communication Association, Singapore, September 14-18, 2014}, pages = {959--963}, publisher = {{ISCA}}, year = {2014}, url = {https://doi.org/10.21437/Interspeech.2014-254}, doi = {10.21437/INTERSPEECH.2014-254}, timestamp = {Fri, 23 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/NgHZKMKVSZNS14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/HsiaoNZRTNS14, author = {Roger Hsiao and Tim Ng and Le Zhang and Shivesh Ranjan and Stavros Tsakalidis and Long Nguyen and Richard M. Schwartz}, editor = {Haizhou Li and Helen M. Meng and Bin Ma and Engsiong Chng and Lei Xie}, title = {Improving semi-supervised deep neural network for keyword search in low resource languages}, booktitle = {{INTERSPEECH} 2014, 15th Annual Conference of the International Speech Communication Association, Singapore, September 14-18, 2014}, pages = {1088--1091}, publisher = {{ISCA}}, year = {2014}, url = {https://doi.org/10.21437/Interspeech.2014-280}, doi = {10.21437/INTERSPEECH.2014-280}, timestamp = {Fri, 23 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/HsiaoNZRTNS14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/asru/KarakosSTZRNHSBNMGHKSVLL13, author = {Damianos G. Karakos and Richard M. Schwartz and Stavros Tsakalidis and Le Zhang and Shivesh Ranjan and Tim Ng and Roger Hsiao and Guruprasad Saikumar and Ivan Bulyko and Long Nguyen and John Makhoul and Frantisek Gr{\'{e}}zl and Mirko Hannemann and Martin Karafi{\'{a}}t and Igor Sz{\"{o}}ke and Karel Vesel{\'{y}} and Lori Lamel and Viet Bac Le}, title = {Score normalization and system combination for improved keyword spotting}, booktitle = {2013 {IEEE} Workshop on Automatic Speech Recognition and Understanding, Olomouc, Czech Republic, December 8-12, 2013}, pages = {210--215}, publisher = {{IEEE}}, year = {2013}, url = {https://doi.org/10.1109/ASRU.2013.6707731}, doi = {10.1109/ASRU.2013.6707731}, timestamp = {Sun, 25 Oct 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/asru/KarakosSTZRNHSBNMGHKSVLL13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/asru/HsiaoNGKTNS13, author = {Roger Hsiao and Tim Ng and Frantisek Gr{\'{e}}zl and Damianos G. Karakos and Stavros Tsakalidis and Long Nguyen and Richard M. Schwartz}, title = {Discriminative semi-supervised training for keyword search in low resource languages}, booktitle = {2013 {IEEE} Workshop on Automatic Speech Recognition and Understanding, Olomouc, Czech Republic, December 8-12, 2013}, pages = {440--445}, publisher = {{IEEE}}, year = {2013}, url = {https://doi.org/10.1109/ASRU.2013.6707770}, doi = {10.1109/ASRU.2013.6707770}, timestamp = {Sun, 22 Mar 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/asru/HsiaoNGKTNS13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/HsiaoS12, author = {Roger Hsiao and Tanja Schultz}, title = {Towards single pass discriminative training for speech recognition}, booktitle = {2012 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2012, Kyoto, Japan, March 25-30, 2012}, pages = {4093--4096}, publisher = {{IEEE}}, year = {2012}, url = {https://doi.org/10.1109/ICASSP.2012.6288818}, doi = {10.1109/ICASSP.2012.6288818}, timestamp = {Sat, 31 Jul 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/HsiaoS12.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/TsakalidisZHWNPN12, author = {Stavros Tsakalidis and Xiaodan Zhuang and Roger Hsiao and Shuang Wu and Pradeep Natarajan and Rohit Prasad and Prem Natarajan}, title = {Robust Event Detection From Spoken Content In Consumer Domain Videos}, booktitle = {{INTERSPEECH} 2012, 13th Annual Conference of the International Speech Communication Association, Portland, Oregon, USA, September 9-13, 2012}, pages = {2101--2104}, publisher = {{ISCA}}, year = {2012}, url = {https://doi.org/10.21437/Interspeech.2012-560}, doi = {10.21437/INTERSPEECH.2012-560}, timestamp = {Fri, 23 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/TsakalidisZHWNPN12.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/HsiaoS11, author = {Roger Hsiao and Tanja Schultz}, title = {Generalized Baum-Welch Algorithm and its Implication to a New Extended Baum-Welch Algorithm}, booktitle = {{INTERSPEECH} 2011, 12th Annual Conference of the International Speech Communication Association, Florence, Italy, August 27-31, 2011}, pages = {773--776}, publisher = {{ISCA}}, year = {2011}, url = {https://doi.org/10.21437/Interspeech.2011-175}, doi = {10.21437/INTERSPEECH.2011-175}, timestamp = {Fri, 23 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/HsiaoS11.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/HsiaoMS10, author = {Roger Hsiao and Florian Metze and Tanja Schultz}, editor = {Takao Kobayashi and Keikichi Hirose and Satoshi Nakamura}, title = {Improvements to generalized discriminative feature transformation for speech recognition}, booktitle = {{INTERSPEECH} 2010, 11th Annual Conference of the International Speech Communication Association, Makuhari, Chiba, Japan, September 26-30, 2010}, pages = {1361--1364}, publisher = {{ISCA}}, year = {2010}, url = {https://doi.org/10.21437/Interspeech.2010-21}, doi = {10.21437/INTERSPEECH.2010-21}, timestamp = {Fri, 23 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/HsiaoMS10.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/MetzeHJNS10, author = {Florian Metze and Roger Hsiao and Qin Jin and Udhyakumar Nallasamy and Tanja Schultz}, editor = {Takao Kobayashi and Keikichi Hirose and Satoshi Nakamura}, title = {The 2010 {CMU} {GALE} speech-to-text system}, booktitle = {{INTERSPEECH} 2010, 11th Annual Conference of the International Speech Communication Association, Makuhari, Chiba, Japan, September 26-30, 2010}, pages = {1501--1504}, publisher = {{ISCA}}, year = {2010}, url = {https://doi.org/10.21437/Interspeech.2010-439}, doi = {10.21437/INTERSPEECH.2010-439}, timestamp = {Fri, 23 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/MetzeHJNS10.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/asru/Al-HajHLBW09, author = {Hassan Al{-}Haj and Roger Hsiao and Ian R. Lane and Alan W. Black and Alex Waibel}, title = {Pronunciation modeling for dialectal arabic speech recognition}, booktitle = {2009 {IEEE} Workshop on Automatic Speech Recognition {\&} Understanding, {ASRU} 2009, Merano/Meran, Italy, December 13-17, 2009}, pages = {525--528}, publisher = {{IEEE}}, year = {2009}, url = {https://doi.org/10.1109/ASRU.2009.5373245}, doi = {10.1109/ASRU.2009.5373245}, timestamp = {Wed, 16 Oct 2019 14:14:51 +0200}, biburl = {https://dblp.org/rec/conf/asru/Al-HajHLBW09.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/HsiaoTS09, author = {Roger Hsiao and Yik{-}Cheung Tam and Tanja Schultz}, title = {Generalized Baum-Welch algorithm for discriminative training on large vocabulary continuous speech recognition system}, booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech, and Signal Processing, {ICASSP} 2009, 19-24 April 2009, Taipei, Taiwan}, pages = {3769--3772}, publisher = {{IEEE}}, year = {2009}, url = {https://doi.org/10.1109/ICASSP.2009.4960447}, doi = {10.1109/ICASSP.2009.4960447}, timestamp = {Thu, 23 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/HsiaoTS09.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/HsiaoS09, author = {Roger Hsiao and Tanja Schultz}, title = {Generalized discriminative feature transformation for speech recognition}, booktitle = {{INTERSPEECH} 2009, 10th Annual Conference of the International Speech Communication Association, Brighton, United Kingdom, September 6-10, 2009}, pages = {664--667}, publisher = {{ISCA}}, year = {2009}, url = {https://doi.org/10.21437/Interspeech.2009-232}, doi = {10.21437/INTERSPEECH.2009-232}, timestamp = {Fri, 23 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/HsiaoS09.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/naacl/BachHECVSLWB09, author = {Nguyen Bach and Roger Hsiao and Matthias Eck and Paisarn Charoenpornsawat and Stephan Vogel and Tanja Schultz and Ian R. Lane and Alex Waibel and Alan W. Black}, title = {Incremental Adaptation of Speech-to-Speech Translation}, booktitle = {Human Language Technologies: Conference of the North American Chapter of the Association of Computational Linguistics, Proceedings, May 31 - June 5, 2009, Boulder, Colorado, USA, Short Papers}, pages = {149--152}, publisher = {The Association for Computational Linguistics}, year = {2009}, url = {https://aclanthology.org/N09-2038/}, timestamp = {Fri, 06 Aug 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/naacl/BachHECVSLWB09.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/HsiaoFTJS08, author = {Roger Hsiao and Mark C. Fuhs and Yik{-}Cheung Tam and Qin Jin and Tanja Schultz}, title = {The CMU-interACT 2008 Mandarin transcription system}, booktitle = {{INTERSPEECH} 2008, 9th Annual Conference of the International Speech Communication Association, Brisbane, Australia, September 22-26, 2008}, pages = {1445--1448}, publisher = {{ISCA}}, year = {2008}, url = {https://doi.org/10.21437/Interspeech.2008-417}, doi = {10.21437/INTERSPEECH.2008-417}, timestamp = {Fri, 23 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/HsiaoFTJS08.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/taslp/MakH07, author = {Brian Kan{-}Wing Mak and Roger Wend{-}Huu Hsiao}, title = {Kernel Eigenspace-Based {MLLR} Adaptation}, journal = {{IEEE} Trans. Speech Audio Process.}, volume = {15}, number = {3}, pages = {784--795}, year = {2007}, url = {https://doi.org/10.1109/TASL.2006.885941}, doi = {10.1109/TASL.2006.885941}, timestamp = {Sun, 17 May 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/taslp/MakH07.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/MakH07, author = {Brian Kan{-}Wing Mak and Roger Wend{-}Huu Hsiao}, title = {Robustness of several kernel-based fast adaptation methods on noisy {LVCSR}}, booktitle = {{INTERSPEECH} 2007, 8th Annual Conference of the International Speech Communication Association, Antwerp, Belgium, August 27-31, 2007}, pages = {266--269}, publisher = {{ISCA}}, year = {2007}, url = {https://doi.org/10.21437/Interspeech.2007-118}, doi = {10.21437/INTERSPEECH.2007-118}, timestamp = {Fri, 23 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/MakH07.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/taslp/MakHHK06, author = {Brian Kan{-}Wing Mak and Roger Wend{-}Huu Hsiao and Simon Ka{-}Lung Ho and James T. Kwok}, title = {Embedded kernel eigenvoice speaker adaptation and its implication to reference speaker weighting}, journal = {{IEEE} Trans. Speech Audio Process.}, volume = {14}, number = {4}, pages = {1267--1280}, year = {2006}, url = {https://doi.org/10.1109/TSA.2005.860836}, doi = {10.1109/TSA.2005.860836}, timestamp = {Sun, 17 May 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/taslp/MakHHK06.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/MakLH06, author = {Brian Mak and Tsz{-}Chung Lai and Roger Wend{-}Huu Hsiao}, title = {Improving Reference Speaker Weighting Adaptation by the Use of Maximum-Likelihood Reference Speakers}, booktitle = {2006 {IEEE} International Conference on Acoustics Speech and Signal Processing, {ICASSP} 2006, Toulouse, France, May 14-19, 2006}, pages = {229--232}, publisher = {{IEEE}}, year = {2006}, url = {https://doi.org/10.1109/ICASSP.2006.1659999}, doi = {10.1109/ICASSP.2006.1659999}, timestamp = {Mon, 22 Jun 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/MakLH06.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/MakHM06, author = {Man{-}Wai Mak and Roger Wend{-}Huu Hsiao and Brian Mak}, title = {A Comparison of Various Adaptation Methods for Speaker Verification With Limited Enrollment Data}, booktitle = {2006 {IEEE} International Conference on Acoustics Speech and Signal Processing, {ICASSP} 2006, Toulouse, France, May 14-19, 2006}, pages = {929--932}, publisher = {{IEEE}}, year = {2006}, url = {https://doi.org/10.1109/ICASSP.2006.1660174}, doi = {10.1109/ICASSP.2006.1660174}, timestamp = {Mon, 22 Jun 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/MakHM06.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/HsiaoVKZCZVBSW06, author = {Roger Hsiao and Ashish Venugopal and Thilo K{\"{o}}hler and Ying Zhang and Paisarn Charoenpornsawat and Andreas Zollmann and Stephan Vogel and Alan W. Black and Tanja Schultz and Alex Waibel}, title = {Optimizing components for handheld two-way speech translation for an English-iraqi Arabic system}, booktitle = {{INTERSPEECH} 2006 - ICSLP, Ninth International Conference on Spoken Language Processing, Pittsburgh, PA, USA, September 17-21, 2006}, publisher = {{ISCA}}, year = {2006}, url = {https://doi.org/10.21437/Interspeech.2006-266}, doi = {10.21437/INTERSPEECH.2006-266}, timestamp = {Thu, 22 Jun 2023 16:42:16 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/HsiaoVKZCZVBSW06.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/HsiaoM05, author = {Roger Wend{-}Huu Hsiao and Brian Kan{-}Wing Mak}, title = {Kernel Eigenspace-based {MLLR} Adaptation Using Multiple Regression Classes}, booktitle = {2005 {IEEE} International Conference on Acoustics, Speech, and Signal Processing, {ICASSP} '05, Philadelphia, Pennsylvania, USA, March 18-23, 2005}, pages = {985--988}, publisher = {{IEEE}}, year = {2005}, url = {https://doi.org/10.1109/ICASSP.2005.1415281}, doi = {10.1109/ICASSP.2005.1415281}, timestamp = {Mon, 22 Jun 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/HsiaoM05.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/HsiaoM05, author = {Roger Wend{-}Huu Hsiao and Brian Kan{-}Wing Mak}, title = {A comparative study of two kernel eigenspace-based speaker adaptation methods on large vocabulary continuous speech recognition}, booktitle = {{INTERSPEECH} 2005 - Eurospeech, 9th European Conference on Speech Communication and Technology, Lisbon, Portugal, September 4-8, 2005}, pages = {1797--1800}, publisher = {{ISCA}}, year = {2005}, url = {https://doi.org/10.21437/Interspeech.2005-166}, doi = {10.21437/INTERSPEECH.2005-166}, timestamp = {Thu, 22 Jun 2023 16:42:16 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/HsiaoM05.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/HsiaoM04, author = {Roger Hsiao and Brian Mak}, title = {Discriminative feature transformation by guided discriminative training}, booktitle = {2004 {IEEE} International Conference on Acoustics, Speech, and Signal Processing, {ICASSP} 2004, Montreal, Quebec, Canada, May 17-21, 2004}, pages = {897--900}, publisher = {{IEEE}}, year = {2004}, url = {https://doi.org/10.1109/ICASSP.2004.1326131}, doi = {10.1109/ICASSP.2004.1326131}, timestamp = {Mon, 22 Jun 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/HsiaoM04.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/MakH04, author = {Brian Kan{-}Wing Mak and Roger Wend{-}Huu Hsiao}, title = {Improving eigenspace-based {MLLR} adaptation by kernel {PCA}}, booktitle = {{INTERSPEECH} 2004 - ICSLP, 8th International Conference on Spoken Language Processing, Jeju Island, Korea, October 4-8, 2004}, pages = {13--16}, publisher = {{ISCA}}, year = {2004}, url = {https://doi.org/10.21437/Interspeech.2004-6}, doi = {10.21437/INTERSPEECH.2004-6}, timestamp = {Thu, 22 Jun 2023 16:42:17 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/MakH04.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/cicc/LinCLLCWCCHL03, author = {M. S. Lin and Ling Chen and J. Y. Lee and H. T. Liu and C. K. Chou and K. H. Wan and H. M. Chen and Kevin Chou and Roger Hsiao and Eric Lin}, title = {A new {IC} interconnection scheme and design architecture for high performance ICs at very low fabrication cost - post passivation interconnection}, booktitle = {Proceedings of the {IEEE} Custom Integrated Circuits Conference, {CICC} 2003, San Jose, CA, USA, September 21 - 24, 2003}, pages = {533--536}, publisher = {{IEEE}}, year = {2003}, url = {https://doi.org/10.1109/CICC.2003.1249454}, doi = {10.1109/CICC.2003.1249454}, timestamp = {Mon, 15 Nov 2021 17:53:34 +0100}, biburl = {https://dblp.org/rec/conf/cicc/LinCLLCWCCHL03.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/MakTH03, author = {Brian Mak and Yik{-}Cheung Tam and Roger Hsiao}, title = {Discriminative training of auditory filters of different shapes for robust speech recognition}, booktitle = {2003 {IEEE} International Conference on Acoustics, Speech, and Signal Processing, {ICASSP} '03, Hong Kong, April 6-10, 2003}, pages = {45--48}, publisher = {{IEEE}}, year = {2003}, url = {https://doi.org/10.1109/ICASSP.2003.1202290}, doi = {10.1109/ICASSP.2003.1202290}, timestamp = {Mon, 22 Jun 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/MakTH03.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.