Stop the war!Остановите войну!
for scientists:
default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDBibTeX records: Michael L. Seltzer
@inproceedings{DBLP:conf/icassp/LeSWLSKS23,
author = {Duc Le and
Frank Seide and
Yuhao Wang and
Yang Li and
Kjell Schubert and
Ozlem Kalinli and
Michael L. Seltzer},
title = {Factorized Blank Thresholding for Improved Runtime Efficiency of Neural
Transducers},
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/ICASSP49357.2023.10095845},
doi = {10.1109/ICASSP49357.2023.10095845},
timestamp = {Fri, 01 Dec 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/LeSWLSKS23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/LiMGSKKSL23,
author = {Ke Li and
Jay Mahadeokar and
Jinxi Guo and
Yangyang Shi and
Gil Keren and
Ozlem Kalinli and
Michael L. Seltzer and
Duc Le},
title = {Improving fast-slow Encoder based Transducer with Streaming Deliberation},
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/ICASSP49357.2023.10095651},
doi = {10.1109/ICASSP49357.2023.10095651},
timestamp = {Sun, 05 Nov 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/LiMGSKKSL23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/TjandraSZKMLS23,
author = {Andros Tjandra and
Nayan Singhal and
David Zhang and
Ozlem Kalinli and
Abdelrahman Mohamed and
Duc Le and
Michael L. Seltzer},
title = {Massively Multilingual {ASR} on 70 Languages: Tokenization, Architecture,
and Generalization Capabilities},
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/ICASSP49357.2023.10094667},
doi = {10.1109/ICASSP49357.2023.10094667},
timestamp = {Sun, 05 Nov 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/TjandraSZKMLS23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2307-12134,
author = {Suyoun Kim and
Akshat Shrivastava and
Duc Le and
Ju Lin and
Ozlem Kalinli and
Michael L. Seltzer},
title = {Modality Confidence Aware Training for Robust End-to-End Spoken Language
Understanding},
journal = {CoRR},
volume = {abs/2307.12134},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2307.12134},
doi = {10.48550/ARXIV.2307.12134},
eprinttype = {arXiv},
eprint = {2307.12134},
timestamp = {Tue, 01 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2307-12134.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2309-09390,
author = {Roshan Sharma and
Suyoun Kim and
Daniel Lazar and
Trang Le and
Akshat Shrivastava and
Kwanghoon Ahn and
Piyush Kansal and
Leda Sari and
Ozlem Kalinli and
Michael L. Seltzer},
title = {Augmenting text for spoken language understanding with Large Language
Models},
journal = {CoRR},
volume = {abs/2309.09390},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2309.09390},
doi = {10.48550/ARXIV.2309.09390},
eprinttype = {arXiv},
eprint = {2309.09390},
timestamp = {Fri, 22 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2309-09390.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2309-10917,
author = {Egor Lakomkin and
Chunyang Wu and
Yassir Fathullah and
Ozlem Kalinli and
Michael L. Seltzer and
Christian Fuegen},
title = {End-to-End Speech Recognition Contextualization with Large Language
Models},
journal = {CoRR},
volume = {abs/2309.10917},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2309.10917},
doi = {10.48550/ARXIV.2309.10917},
eprinttype = {arXiv},
eprint = {2309.10917},
timestamp = {Tue, 26 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2309-10917.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/BruguierLPLLWCP22,
author = {Antoine Bruguier and
Duc Le and
Rohit Prabhavalkar and
Dangna Li and
Zhe Liu and
Bo Wang and
Eun Chang and
Fuchun Peng and
Ozlem Kalinli and
Michael L. Seltzer},
title = {Neural-FST Class Language Model for End-to-End Speech Recognition},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2022, Virtual and Singapore, 23-27 May 2022},
pages = {6107--6111},
publisher = {{IEEE}},
year = {2022},
url = {https://doi.org/10.1109/ICASSP43922.2022.9747573},
doi = {10.1109/ICASSP43922.2022.9747573},
timestamp = {Wed, 05 Oct 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/BruguierLPLLWCP22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/MahadeokarSLLZC22,
author = {Jay Mahadeokar and
Yangyang Shi and
Ke Li and
Duc Le and
Jiedan Zhu and
Vikas Chandra and
Ozlem Kalinli and
Michael L. Seltzer},
editor = {Hanseok Ko and
John H. L. Hansen},
title = {Streaming parallel transducer beam search with fast slow cascaded
encoders},
booktitle = {Interspeech 2022, 23rd Annual Conference of the International Speech
Communication Association, Incheon, Korea, 18-22 September 2022},
pages = {2083--2087},
publisher = {{ISCA}},
year = {2022},
url = {https://doi.org/10.21437/Interspeech.2022-10551},
doi = {10.21437/INTERSPEECH.2022-10551},
timestamp = {Wed, 21 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/MahadeokarSLLZC22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/LeSTKLKS22,
author = {Duc Le and
Akshat Shrivastava and
Paden D. Tomasello and
Suyoun Kim and
Aleksandr Livshits and
Ozlem Kalinli and
Michael L. Seltzer},
editor = {Hanseok Ko and
John H. L. Hansen},
title = {Deliberation Model for On-Device Spoken Language Understanding},
booktitle = {Interspeech 2022, 23rd Annual Conference of the International Speech
Communication Association, Incheon, Korea, 18-22 September 2022},
pages = {3468--3472},
publisher = {{ISCA}},
year = {2022},
url = {https://doi.org/10.21437/Interspeech.2022-10800},
doi = {10.21437/INTERSPEECH.2022-10800},
timestamp = {Wed, 21 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/LeSTKLKS22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/KimLZSAZFKS22,
author = {Suyoun Kim and
Duc Le and
Weiyi Zheng and
Tarun Singh and
Abhinav Arora and
Xiaoyu Zhai and
Christian Fuegen and
Ozlem Kalinli and
Michael L. Seltzer},
editor = {Hanseok Ko and
John H. L. Hansen},
title = {Evaluating User Perception of Speech Recognition System Quality with
Semantic Distance Metric},
booktitle = {Interspeech 2022, 23rd Annual Conference of the International Speech
Communication Association, Incheon, Korea, 18-22 September 2022},
pages = {3978--3982},
publisher = {{ISCA}},
year = {2022},
url = {https://doi.org/10.21437/Interspeech.2022-11144},
doi = {10.21437/INTERSPEECH.2022-11144},
timestamp = {Wed, 21 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/KimLZSAZFKS22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2201-11867,
author = {Antoine Bruguier and
Duc Le and
Rohit Prabhavalkar and
Dangna Li and
Zhe Liu and
Bo Wang and
Eun Chang and
Fuchun Peng and
Ozlem Kalinli and
Michael L. Seltzer},
title = {Neural-FST Class Language Model for End-to-End Speech Recognition},
journal = {CoRR},
volume = {abs/2201.11867},
year = {2022},
url = {https://arxiv.org/abs/2201.11867},
eprinttype = {arXiv},
eprint = {2201.11867},
timestamp = {Wed, 05 Oct 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2201-11867.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2203-15773,
author = {Jay Mahadeokar and
Yangyang Shi and
Ke Li and
Duc Le and
Jiedan Zhu and
Vikas Chandra and
Ozlem Kalinli and
Michael L. Seltzer},
title = {Streaming parallel transducer beam search with fast-slow cascaded
encoders},
journal = {CoRR},
volume = {abs/2203.15773},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2203.15773},
doi = {10.48550/ARXIV.2203.15773},
eprinttype = {arXiv},
eprint = {2203.15773},
timestamp = {Mon, 04 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2203-15773.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2204-01893,
author = {Duc Le and
Akshat Shrivastava and
Paden Tomasello and
Suyoun Kim and
Aleksandr Livshits and
Ozlem Kalinli and
Michael L. Seltzer},
title = {Deliberation Model for On-Device Spoken Language Understanding},
journal = {CoRR},
volume = {abs/2204.01893},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2204.01893},
doi = {10.48550/ARXIV.2204.01893},
eprinttype = {arXiv},
eprint = {2204.01893},
timestamp = {Wed, 06 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2204-01893.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2211-00896,
author = {Duc Le and
Frank Seide and
Yuhao Wang and
Yang Li and
Kjell Schubert and
Ozlem Kalinli and
Michael L. Seltzer},
title = {Factorized Blank Thresholding for Improved Runtime Efficiency of Neural
Transducers},
journal = {CoRR},
volume = {abs/2211.00896},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2211.00896},
doi = {10.48550/ARXIV.2211.00896},
eprinttype = {arXiv},
eprint = {2211.00896},
timestamp = {Tue, 04 Jul 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2211-00896.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2211-05756,
author = {Andros Tjandra and
Nayan Singhal and
David Zhang and
Ozlem Kalinli and
Abdelrahman Mohamed and
Duc Le and
Michael L. Seltzer},
title = {Massively Multilingual {ASR} on 70 Languages: Tokenization, Architecture,
and Generalization Capabilities},
journal = {CoRR},
volume = {abs/2211.05756},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2211.05756},
doi = {10.48550/ARXIV.2211.05756},
eprinttype = {arXiv},
eprint = {2211.05756},
timestamp = {Tue, 15 Nov 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2211-05756.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/KimSMBFSL21,
author = {Suyoun Kim and
Yuan Shangguan and
Jay Mahadeokar and
Antoine Bruguier and
Christian Fuegen and
Michael L. Seltzer and
Duc Le},
title = {Improved Neural Language Model Fusion for Streaming Recurrent Neural
Network Transducer},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2021, Toronto, ON, Canada, June 6-11, 2021},
pages = {7333--7337},
publisher = {{IEEE}},
year = {2021},
url = {https://doi.org/10.1109/ICASSP39728.2021.9414784},
doi = {10.1109/ICASSP39728.2021.9414784},
timestamp = {Fri, 09 Jul 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/KimSMBFSL21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/VenkateshVMSFSC21,
author = {Ganesh Venkatesh and
Alagappan Valliappan and
Jay Mahadeokar and
Yuan Shangguan and
Christian Fuegen and
Michael L. Seltzer and
Vikas Chandra},
title = {Memory-Efficient Speech Recognition on Smart Devices},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2021, Toronto, ON, Canada, June 6-11, 2021},
pages = {8368--8372},
publisher = {{IEEE}},
year = {2021},
url = {https://doi.org/10.1109/ICASSP39728.2021.9414502},
doi = {10.1109/ICASSP39728.2021.9414502},
timestamp = {Fri, 09 Jul 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/VenkateshVMSFSC21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/LeJKKSMCSFKSS21,
author = {Duc Le and
Mahaveer Jain and
Gil Keren and
Suyoun Kim and
Yangyang Shi and
Jay Mahadeokar and
Julian Chan and
Yuan Shangguan and
Christian Fuegen and
Ozlem Kalinli and
Yatharth Saraf and
Michael L. Seltzer},
editor = {Hynek Hermansky and
Honza Cernock{\'{y}} and
Luk{\'{a}}s Burget and
Lori Lamel and
Odette Scharenborg and
Petr Motl{\'{\i}}cek},
title = {Contextualized Streaming End-to-End Speech Recognition with Trie-Based
Deep Biasing and Shallow Fusion},
booktitle = {Interspeech 2021, 22nd Annual Conference of the International Speech
Communication Association, Brno, Czechia, 30 August - 3 September
2021},
pages = {1772--1776},
publisher = {{ISCA}},
year = {2021},
url = {https://doi.org/10.21437/Interspeech.2021-1566},
doi = {10.21437/INTERSPEECH.2021-1566},
timestamp = {Wed, 21 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/LeJKKSMCSFKSS21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/KimALYFKS21,
author = {Suyoun Kim and
Abhinav Arora and
Duc Le and
Ching{-}Feng Yeh and
Christian Fuegen and
Ozlem Kalinli and
Michael L. Seltzer},
editor = {Hynek Hermansky and
Honza Cernock{\'{y}} and
Luk{\'{a}}s Burget and
Lori Lamel and
Odette Scharenborg and
Petr Motl{\'{\i}}cek},
title = {Semantic Distance: {A} New Metric for {ASR} Performance Analysis Towards
Spoken Language Understanding},
booktitle = {Interspeech 2021, 22nd Annual Conference of the International Speech
Communication Association, Brno, Czechia, 30 August - 3 September
2021},
pages = {1977--1981},
publisher = {{ISCA}},
year = {2021},
url = {https://doi.org/10.21437/Interspeech.2021-1929},
doi = {10.21437/INTERSPEECH.2021-1929},
timestamp = {Wed, 21 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/KimALYFKS21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/ShiNWMLPXYCFKS21,
author = {Yangyang Shi and
Varun Nagaraja and
Chunyang Wu and
Jay Mahadeokar and
Duc Le and
Rohit Prabhavalkar and
Alex Xiao and
Ching{-}Feng Yeh and
Julian Chan and
Christian Fuegen and
Ozlem Kalinli and
Michael L. Seltzer},
editor = {Hynek Hermansky and
Honza Cernock{\'{y}} and
Luk{\'{a}}s Burget and
Lori Lamel and
Odette Scharenborg and
Petr Motl{\'{\i}}cek},
title = {Dynamic Encoder Transducer: {A} Flexible Solution for Trading Off
Accuracy for Latency},
booktitle = {Interspeech 2021, 22nd Annual Conference of the International Speech
Communication Association, Brno, Czechia, 30 August - 3 September
2021},
pages = {2042--2046},
publisher = {{ISCA}},
year = {2021},
url = {https://doi.org/10.21437/Interspeech.2021-1272},
doi = {10.21437/INTERSPEECH.2021-1272},
timestamp = {Wed, 21 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/ShiNWMLPXYCFKS21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/MahadeokarSSWXS21,
author = {Jay Mahadeokar and
Yangyang Shi and
Yuan Shangguan and
Chunyang Wu and
Alex Xiao and
Hang Su and
Duc Le and
Ozlem Kalinli and
Christian Fuegen and
Michael L. Seltzer},
editor = {Hynek Hermansky and
Honza Cernock{\'{y}} and
Luk{\'{a}}s Burget and
Lori Lamel and
Odette Scharenborg and
Petr Motl{\'{\i}}cek},
title = {Flexi-Transducer: Optimizing Latency, Accuracy and Compute for Multi-Domain
On-Device Scenarios},
booktitle = {Interspeech 2021, 22nd Annual Conference of the International Speech
Communication Association, Brno, Czechia, 30 August - 3 September
2021},
pages = {2107--2111},
publisher = {{ISCA}},
year = {2021},
url = {https://doi.org/10.21437/Interspeech.2021-1921},
doi = {10.21437/INTERSPEECH.2021-1921},
timestamp = {Wed, 21 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/MahadeokarSSWXS21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/ShangguanPSMSZW21,
author = {Yuan Shangguan and
Rohit Prabhavalkar and
Hang Su and
Jay Mahadeokar and
Yangyang Shi and
Jiatong Zhou and
Chunyang Wu and
Duc Le and
Ozlem Kalinli and
Christian Fuegen and
Michael L. Seltzer},
editor = {Hynek Hermansky and
Honza Cernock{\'{y}} and
Luk{\'{a}}s Burget and
Lori Lamel and
Odette Scharenborg and
Petr Motl{\'{\i}}cek},
title = {Dissecting User-Perceived Latency of On-Device {E2E} Speech Recognition},
booktitle = {Interspeech 2021, 22nd Annual Conference of the International Speech
Communication Association, Brno, Czechia, 30 August - 3 September
2021},
pages = {4553--4557},
publisher = {{ISCA}},
year = {2021},
url = {https://doi.org/10.21437/Interspeech.2021-1887},
doi = {10.21437/INTERSPEECH.2021-1887},
timestamp = {Wed, 21 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/ShangguanPSMSZW21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/NagarajaSVKSC21,
author = {Varun Nagaraja and
Yangyang Shi and
Ganesh Venkatesh and
Ozlem Kalinli and
Michael L. Seltzer and
Vikas Chandra},
editor = {Hynek Hermansky and
Honza Cernock{\'{y}} and
Luk{\'{a}}s Burget and
Lori Lamel and
Odette Scharenborg and
Petr Motl{\'{\i}}cek},
title = {Collaborative Training of Acoustic Encoders for Speech Recognition},
booktitle = {Interspeech 2021, 22nd Annual Conference of the International Speech
Communication Association, Brno, Czechia, 30 August - 3 September
2021},
pages = {4573--4577},
publisher = {{ISCA}},
year = {2021},
url = {https://doi.org/10.21437/Interspeech.2021-354},
doi = {10.21437/INTERSPEECH.2021-354},
timestamp = {Wed, 21 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/NagarajaSVKSC21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/slt/YehWSW0CS21,
author = {Ching{-}Feng Yeh and
Yongqiang Wang and
Yangyang Shi and
Chunyang Wu and
Frank Zhang and
Julian Chan and
Michael L. Seltzer},
title = {Streaming Attention-Based Models with Augmented Memory for End-To-End
Speech Recognition},
booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen,
China, January 19-22, 2021},
pages = {8--14},
publisher = {{IEEE}},
year = {2021},
url = {https://doi.org/10.1109/SLT48900.2021.9383504},
doi = {10.1109/SLT48900.2021.9383504},
timestamp = {Wed, 02 Nov 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/slt/YehWSW0CS21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/slt/MahadeokarSLKSL21,
author = {Jay Mahadeokar and
Yuan Shangguan and
Duc Le and
Gil Keren and
Hang Su and
Thong Le and
Ching{-}Feng Yeh and
Christian Fuegen and
Michael L. Seltzer},
title = {Alignment Restricted Streaming Recurrent Neural Network Transducer},
booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen,
China, January 19-22, 2021},
pages = {52--59},
publisher = {{IEEE}},
year = {2021},
url = {https://doi.org/10.1109/SLT48900.2021.9383606},
doi = {10.1109/SLT48900.2021.9383606},
timestamp = {Thu, 08 Apr 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/slt/MahadeokarSLKSL21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/slt/LeKCMFS21,
author = {Duc Le and
Gil Keren and
Julian Chan and
Jay Mahadeokar and
Christian Fuegen and
Michael L. Seltzer},
title = {Deep Shallow Fusion for {RNN-T} Personalization},
booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen,
China, January 19-22, 2021},
pages = {251--257},
publisher = {{IEEE}},
year = {2021},
url = {https://doi.org/10.1109/SLT48900.2021.9383560},
doi = {10.1109/SLT48900.2021.9383560},
timestamp = {Thu, 08 Apr 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/slt/LeKCMFS21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2102-11531,
author = {Ganesh Venkatesh and
Alagappan Valliappan and
Jay Mahadeokar and
Yuan Shangguan and
Christian Fuegen and
Michael L. Seltzer and
Vikas Chandra},
title = {Memory-efficient Speech Recognition on Smart Devices},
journal = {CoRR},
volume = {abs/2102.11531},
year = {2021},
url = {https://arxiv.org/abs/2102.11531},
eprinttype = {arXiv},
eprint = {2102.11531},
timestamp = {Wed, 24 Feb 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2102-11531.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2104-02138,
author = {Suyoun Kim and
Abhinav Arora and
Duc Le and
Ching{-}Feng Yeh and
Christian Fuegen and
Ozlem Kalinli and
Michael L. Seltzer},
title = {Semantic Distance: {A} New Metric for {ASR} Performance Analysis Towards
Spoken Language Understanding},
journal = {CoRR},
volume = {abs/2104.02138},
year = {2021},
url = {https://arxiv.org/abs/2104.02138},
eprinttype = {arXiv},
eprint = {2104.02138},
timestamp = {Mon, 12 Apr 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2104-02138.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2104-02176,
author = {Yangyang Shi and
Varun Nagaraja and
Chunyang Wu and
Jay Mahadeokar and
Duc Le and
Rohit Prabhavalkar and
Alex Xiao and
Ching{-}Feng Yeh and
Julian Chan and
Christian Fuegen and
Ozlem Kalinli and
Michael L. Seltzer},
title = {Dynamic Encoder Transducer: {A} Flexible Solution For Trading Off
Accuracy For Latency},
journal = {CoRR},
volume = {abs/2104.02176},
year = {2021},
url = {https://arxiv.org/abs/2104.02176},
eprinttype = {arXiv},
eprint = {2104.02176},
timestamp = {Mon, 12 Apr 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2104-02176.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2104-02194,
author = {Duc Le and
Mahaveer Jain and
Gil Keren and
Suyoun Kim and
Yangyang Shi and
Jay Mahadeokar and
Julian Chan and
Yuan Shangguan and
Christian Fuegen and
Ozlem Kalinli and
Yatharth Saraf and
Michael L. Seltzer},
title = {Contextualized Streaming End-to-End Speech Recognition with Trie-Based
Deep Biasing and Shallow Fusion},
journal = {CoRR},
volume = {abs/2104.02194},
year = {2021},
url = {https://arxiv.org/abs/2104.02194},
eprinttype = {arXiv},
eprint = {2104.02194},
timestamp = {Mon, 12 Apr 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2104-02194.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2104-02207,
author = {Yuan Shangguan and
Rohit Prabhavalkar and
Hang Su and
Jay Mahadeokar and
Yangyang Shi and
Jiatong Zhou and
Chunyang Wu and
Duc Le and
Ozlem Kalinli and
Christian Fuegen and
Michael L. Seltzer},
title = {Dissecting User-Perceived Latency of On-Device {E2E} Speech Recognition},
journal = {CoRR},
volume = {abs/2104.02207},
year = {2021},
url = {https://arxiv.org/abs/2104.02207},
eprinttype = {arXiv},
eprint = {2104.02207},
timestamp = {Mon, 12 Apr 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2104-02207.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2104-02232,
author = {Jay Mahadeokar and
Yangyang Shi and
Yuan Shangguan and
Chunyang Wu and
Alex Xiao and
Hang Su and
Duc Le and
Ozlem Kalinli and
Christian Fuegen and
Michael L. Seltzer},
title = {Flexi-Transducer: Optimizing Latency, Accuracy and Compute forMulti-Domain
On-Device Scenarios},
journal = {CoRR},
volume = {abs/2104.02232},
year = {2021},
url = {https://arxiv.org/abs/2104.02232},
eprinttype = {arXiv},
eprint = {2104.02232},
timestamp = {Mon, 12 Apr 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2104-02232.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2106-08960,
author = {Varun Nagaraja and
Yangyang Shi and
Ganesh Venkatesh and
Ozlem Kalinli and
Michael L. Seltzer and
Vikas Chandra},
title = {Collaborative Training of Acoustic Encoders for Speech Recognition},
journal = {CoRR},
volume = {abs/2106.08960},
year = {2021},
url = {https://arxiv.org/abs/2106.08960},
eprinttype = {arXiv},
eprint = {2106.08960},
timestamp = {Tue, 29 Jun 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2106-08960.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2110-05376,
author = {Suyoun Kim and
Duc Le and
Weiyi Zheng and
Tarun Singh and
Abhinav Arora and
Xiaoyu Zhai and
Christian Fuegen and
Ozlem Kalinli and
Michael L. Seltzer},
title = {Evaluating User Perception of Speech Recognition System Quality with
Semantic Distance Metric},
journal = {CoRR},
volume = {abs/2110.05376},
year = {2021},
url = {https://arxiv.org/abs/2110.05376},
eprinttype = {arXiv},
eprint = {2110.05376},
timestamp = {Thu, 21 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2110-05376.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/LeKFS20,
author = {Duc Le and
Thilo K{\"{o}}hler and
Christian Fuegen and
Michael L. Seltzer},
title = {{G2G:} TTS-Driven Pronunciation Learning for Graphemic Hybrid {ASR}},
booktitle = {2020 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2020, Barcelona, Spain, May 4-8, 2020},
pages = {6869--6873},
publisher = {{IEEE}},
year = {2020},
url = {https://doi.org/10.1109/ICASSP40776.2020.9054257},
doi = {10.1109/ICASSP40776.2020.9054257},
timestamp = {Wed, 10 Feb 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/LeKFS20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/WangMLLXMHTZZFZ20,
author = {Yongqiang Wang and
Abdelrahman Mohamed and
Duc Le and
Chunxi Liu and
Alex Xiao and
Jay Mahadeokar and
Hongzhao Huang and
Andros Tjandra and
Xiaohui Zhang and
Frank Zhang and
Christian Fuegen and
Geoffrey Zweig and
Michael L. Seltzer},
title = {Transformer-Based Acoustic Modeling for Hybrid Speech Recognition},
booktitle = {2020 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2020, Barcelona, Spain, May 4-8, 2020},
pages = {6874--6878},
publisher = {{IEEE}},
year = {2020},
url = {https://doi.org/10.1109/ICASSP40776.2020.9054345},
doi = {10.1109/ICASSP40776.2020.9054345},
timestamp = {Thu, 04 Apr 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/WangMLLXMHTZZFZ20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/ChenYYJS20,
author = {Yi{-}Chen Chen and
Zhaojun Yang and
Ching{-}Feng Yeh and
Mahaveer Jain and
Michael L. Seltzer},
title = {Aipnet: Generative Adversarial Pre-Training of Accent-Invariant Networks
for End-To-End Speech Recognition},
booktitle = {2020 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2020, Barcelona, Spain, May 4-8, 2020},
pages = {6979--6983},
publisher = {{IEEE}},
year = {2020},
url = {https://doi.org/10.1109/ICASSP40776.2020.9053098},
doi = {10.1109/ICASSP40776.2020.9053098},
timestamp = {Thu, 23 Jul 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/ChenYYJS20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/ShiWWFZLYS20,
author = {Yangyang Shi and
Yongqiang Wang and
Chunyang Wu and
Christian Fuegen and
Frank Zhang and
Duc Le and
Ching{-}Feng Yeh and
Michael L. Seltzer},
editor = {Helen Meng and
Bo Xu and
Thomas Fang Zheng},
title = {Weak-Attention Suppression for Transformer Based Speech Recognition},
booktitle = {Interspeech 2020, 21st Annual Conference of the International Speech
Communication Association, Virtual Event, Shanghai, China, 25-29 October
2020},
pages = {4996--5000},
publisher = {{ISCA}},
year = {2020},
url = {https://doi.org/10.21437/Interspeech.2020-1363},
doi = {10.21437/INTERSPEECH.2020-1363},
timestamp = {Wed, 02 Nov 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/interspeech/ShiWWFZLYS20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2005-09137,
author = {Yangyang Shi and
Yongqiang Wang and
Chunyang Wu and
Christian Fuegen and
Frank Zhang and
Duc Le and
Ching{-}Feng Yeh and
Michael L. Seltzer},
title = {Weak-Attention Suppression For Transformer Based Speech Recognition},
journal = {CoRR},
volume = {abs/2005.09137},
year = {2020},
url = {https://arxiv.org/abs/2005.09137},
eprinttype = {arXiv},
eprint = {2005.09137},
timestamp = {Wed, 02 Nov 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2005-09137.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2010-10759,
author = {Yangyang Shi and
Yongqiang Wang and
Chunyang Wu and
Ching{-}Feng Yeh and
Julian Chan and
Frank Zhang and
Duc Le and
Michael L. Seltzer},
title = {Emformer: Efficient Memory Transformer Based Acoustic Model For Low
Latency Streaming Speech Recognition},
journal = {CoRR},
volume = {abs/2010.10759},
year = {2020},
url = {https://arxiv.org/abs/2010.10759},
eprinttype = {arXiv},
eprint = {2010.10759},
timestamp = {Wed, 02 Nov 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2010-10759.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2010-13878,
author = {Suyoun Kim and
Yuan Shangguan and
Jay Mahadeokar and
Antoine Bruguier and
Christian Fuegen and
Michael L. Seltzer and
Duc Le},
title = {Improved Neural Language Model Fusion for Streaming Recurrent Neural
Network Transducer},
journal = {CoRR},
volume = {abs/2010.13878},
year = {2020},
url = {https://arxiv.org/abs/2010.13878},
eprinttype = {arXiv},
eprint = {2010.13878},
timestamp = {Mon, 02 Nov 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2010-13878.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2011-03072,
author = {Jay Mahadeokar and
Yuan Shangguan and
Duc Le and
Gil Keren and
Hang Su and
Thong Le and
Ching{-}Feng Yeh and
Christian Fuegen and
Michael L. Seltzer},
title = {Alignment Restricted Streaming Recurrent Neural Network Transducer},
journal = {CoRR},
volume = {abs/2011.03072},
year = {2020},
url = {https://arxiv.org/abs/2011.03072},
eprinttype = {arXiv},
eprint = {2011.03072},
timestamp = {Thu, 12 Nov 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2011-03072.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2011-07120,
author = {Ching{-}Feng Yeh and
Yongqiang Wang and
Yangyang Shi and
Chunyang Wu and
Frank Zhang and
Julian Chan and
Michael L. Seltzer},
title = {Streaming Attention-Based Models with Augmented Memory for End-to-End
Speech Recognition},
journal = {CoRR},
volume = {abs/2011.07120},
year = {2020},
url = {https://arxiv.org/abs/2011.07120},
eprinttype = {arXiv},
eprint = {2011.07120},
timestamp = {Wed, 02 Nov 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2011-07120.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2011-07754,
author = {Duc Le and
Gil Keren and
Julian Chan and
Jay Mahadeokar and
Christian Fuegen and
Michael L. Seltzer},
title = {Deep Shallow Fusion for {RNN-T} Personalization},
journal = {CoRR},
volume = {abs/2011.07754},
year = {2020},
url = {https://arxiv.org/abs/2011.07754},
eprinttype = {arXiv},
eprint = {2011.07754},
timestamp = {Wed, 18 Nov 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2011-07754.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jstsp/WatanabeABHS19,
author = {Shinji Watanabe and
Shoko Araki and
Michiel Bacchiani and
Reinhold Haeb{-}Umbach and
Michael L. Seltzer},
title = {Introduction to the Issue on Far-Field Speech Processing in the Era
of Deep Learning: Speech Enhancement, Separation, and Recognition},
journal = {{IEEE} J. Sel. Top. Signal Process.},
volume = {13},
number = {4},
pages = {785--786},
year = {2019},
url = {https://doi.org/10.1109/JSTSP.2019.2925640},
doi = {10.1109/JSTSP.2019.2925640},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/jstsp/WatanabeABHS19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/spm/Haeb-UmbachWNBH19,
author = {Reinhold Haeb{-}Umbach and
Shinji Watanabe and
Tomohiro Nakatani and
Michiel Bacchiani and
Bj{\"{o}}rn Hoffmeister and
Michael L. Seltzer and
Heiga Zen and
Mehrez Souden},
title = {Speech Processing for Digital Home Assistants: Combining signal processing
with deep-learning techniques},
journal = {{IEEE} Signal Process. Mag.},
volume = {36},
number = {6},
pages = {111--124},
year = {2019},
url = {https://doi.org/10.1109/MSP.2019.2918706},
doi = {10.1109/MSP.2019.2918706},
timestamp = {Fri, 26 Jun 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/spm/Haeb-UmbachWNBH19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/asru/LeZZFZS19,
author = {Duc Le and
Xiaohui Zhang and
Weiyi Zheng and
Christian F{\"{u}}gen and
Geoffrey Zweig and
Michael L. Seltzer},
title = {From Senones to Chenones: Tied Context-Dependent Graphemes for Hybrid
Speech Recognition},
booktitle = {{IEEE} Automatic Speech Recognition and Understanding Workshop, {ASRU}
2019, Singapore, December 14-18, 2019},
pages = {457--464},
publisher = {{IEEE}},
year = {2019},
url = {https://doi.org/10.1109/ASRU46091.2019.9003972},
doi = {10.1109/ASRU46091.2019.9003972},
timestamp = {Thu, 04 Apr 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/asru/LeZZFZS19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/ChenJWSF19,
author = {Zhehuai Chen and
Mahaveer Jain and
Yongqiang Wang and
Michael L. Seltzer and
Christian Fuegen},
title = {End-to-end Contextual Speech Recognition Using Class Language Models
and a Token Passing Decoder},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2019, Brighton, United Kingdom, May 12-17, 2019},
pages = {6186--6190},
publisher = {{IEEE}},
year = {2019},
url = {https://doi.org/10.1109/ICASSP.2019.8683573},
doi = {10.1109/ICASSP.2019.8683573},
timestamp = {Wed, 02 Nov 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/ChenJWSF19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/ChenJWSF19,
author = {Zhehuai Chen and
Mahaveer Jain and
Yongqiang Wang and
Michael L. Seltzer and
Christian Fuegen},
editor = {Gernot Kubin and
Zdravko Kacic},
title = {Joint Grapheme and Phoneme Embeddings for Contextual End-to-End {ASR}},
booktitle = {Interspeech 2019, 20th Annual Conference of the International Speech
Communication Association, Graz, Austria, 15-19 September 2019},
pages = {3490--3494},
publisher = {{ISCA}},
year = {2019},
url = {https://doi.org/10.21437/Interspeech.2019-1434},
doi = {10.21437/INTERSPEECH.2019-1434},
timestamp = {Wed, 02 Nov 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/interspeech/ChenJWSF19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1910-01493,
author = {Duc Le and
Xiaohui Zhang and
Weiyi Zheng and
Christian F{\"{u}}gen and
Geoffrey Zweig and
Michael L. Seltzer},
title = {From Senones to Chenones: Tied Context-Dependent Graphemes for Hybrid
Speech Recognition},
journal = {CoRR},
volume = {abs/1910.01493},
year = {2019},
url = {http://arxiv.org/abs/1910.01493},
eprinttype = {arXiv},
eprint = {1910.01493},
timestamp = {Thu, 04 Apr 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1910-01493.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1910-09799,
author = {Yongqiang Wang and
Abdelrahman Mohamed and
Duc Le and
Chunxi Liu and
Alex Xiao and
Jay Mahadeokar and
Hongzhao Huang and
Andros Tjandra and
Xiaohui Zhang and
Frank Zhang and
Christian Fuegen and
Geoffrey Zweig and
Michael L. Seltzer},
title = {Transformer-based Acoustic Modeling for Hybrid Speech Recognition},
journal = {CoRR},
volume = {abs/1910.09799},
year = {2019},
url = {http://arxiv.org/abs/1910.09799},
eprinttype = {arXiv},
eprint = {1910.09799},
timestamp = {Thu, 04 Apr 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1910-09799.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1910-12612,
author = {Duc Le and
Thilo K{\"{o}}hler and
Christian Fuegen and
Michael L. Seltzer},
title = {{G2G:} TTS-Driven Pronunciation Learning for Graphemic Hybrid {ASR}},
journal = {CoRR},
volume = {abs/1910.12612},
year = {2019},
url = {http://arxiv.org/abs/1910.12612},
eprinttype = {arXiv},
eprint = {1910.12612},
timestamp = {Thu, 31 Oct 2019 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1910-12612.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1910-12977,
author = {Ching{-}Feng Yeh and
Jay Mahadeokar and
Kaustubh Kalgaonkar and
Yongqiang Wang and
Duc Le and
Mahaveer Jain and
Kjell Schubert and
Christian Fuegen and
Michael L. Seltzer},
title = {Transformer-Transducer: End-to-End Speech Recognition with Self-Attention},
journal = {CoRR},
volume = {abs/1910.12977},
year = {2019},
url = {http://arxiv.org/abs/1910.12977},
eprinttype = {arXiv},
eprint = {1910.12977},
timestamp = {Wed, 02 Nov 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1910-12977.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1911-01629,
author = {Mahaveer Jain and
Kjell Schubert and
Jay Mahadeokar and
Ching{-}Feng Yeh and
Kaustubh Kalgaonkar and
Anuroop Sriram and
Christian Fuegen and
Michael L. Seltzer},
title = {{RNN-T} For Latency Controlled {ASR} With Improved Beam Search},
journal = {CoRR},
volume = {abs/1911.01629},
year = {2019},
url = {http://arxiv.org/abs/1911.01629},
eprinttype = {arXiv},
eprint = {1911.01629},
timestamp = {Mon, 11 Nov 2019 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1911-01629.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1911-11935,
author = {Yi{-}Chen Chen and
Zhaojun Yang and
Ching{-}Feng Yeh and
Mahaveer Jain and
Michael L. Seltzer},
title = {AIPNet: Generative Adversarial Pre-training of Accent-invariant Networks
for End-to-end Speech Recognition},
journal = {CoRR},
volume = {abs/1911.11935},
year = {2019},
url = {http://arxiv.org/abs/1911.11935},
eprinttype = {arXiv},
eprint = {1911.11935},
timestamp = {Tue, 03 Dec 2019 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1911-11935.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/KimS18a,
author = {Suyoun Kim and
Michael L. Seltzer},
title = {Towards Language-Universal End-to-End Speech Recognition},
booktitle = {2018 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2018, Calgary, AB, Canada, April 15-20, 2018},
pages = {4914--4918},
publisher = {{IEEE}},
year = {2018},
url = {https://doi.org/10.1109/ICASSP.2018.8462201},
doi = {10.1109/ICASSP.2018.8462201},
timestamp = {Wed, 16 Oct 2019 14:14:52 +0200},
biburl = {https://dblp.org/rec/conf/icassp/KimS18a.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/ChenYXLSG18,
author = {Zhuo Chen and
Takuya Yoshioka and
Xiong Xiao and
Linyu Li and
Michael L. Seltzer and
Yifan Gong},
title = {Efficient Integration of Fixed Beamformers and Speech Separation Networks
for Multi-Channel Far-Field Speech Separation},
booktitle = {2018 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2018, Calgary, AB, Canada, April 15-20, 2018},
pages = {5384--5388},
publisher = {{IEEE}},
year = {2018},
url = {https://doi.org/10.1109/ICASSP.2018.8461930},
doi = {10.1109/ICASSP.2018.8461930},
timestamp = {Tue, 04 May 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/ChenYXLSG18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/KimSLZ18,
author = {Suyoun Kim and
Michael L. Seltzer and
Jinyu Li and
Rui Zhao},
editor = {B. Yegnanarayana},
title = {Improved Training for Online End-to-end Speech Recognition Systems},
booktitle = {Interspeech 2018, 19th Annual Conference of the International Speech
Communication Association, Hyderabad, India, 2-6 September 2018},
pages = {2913--2917},
publisher = {{ISCA}},
year = {2018},
url = {https://doi.org/10.21437/Interspeech.2018-2517},
doi = {10.21437/INTERSPEECH.2018-2517},
timestamp = {Tue, 21 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/interspeech/KimSLZ18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1812-02142,
author = {Zhehuai Chen and
Mahaveer Jain and
Yongqiang Wang and
Michael L. Seltzer and
Christian Fuegen},
title = {End-to-end contextual speech recognition using class language models
and a token passing decoder},
journal = {CoRR},
volume = {abs/1812.02142},
year = {2018},
url = {http://arxiv.org/abs/1812.02142},
eprinttype = {arXiv},
eprint = {1812.02142},
timestamp = {Wed, 02 Nov 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1812-02142.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/taslp/XiongDHSSSYZ17,
author = {Wayne Xiong and
Jasha Droppo and
Xuedong Huang and
Frank Seide and
Michael L. Seltzer and
Andreas Stolcke and
Dong Yu and
Geoffrey Zweig},
title = {Toward Human Parity in Conversational Speech Recognition},
journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.},
volume = {25},
number = {12},
pages = {2410--2423},
year = {2017},
url = {https://doi.org/10.1109/TASLP.2017.2756440},
doi = {10.1109/TASLP.2017.2756440},
timestamp = {Mon, 26 Oct 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/taslp/XiongDHSSSYZ17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/eacl/WongPZSJ17,
author = {Baolin Peng and
Michael L. Seltzer and
Y. C. Ju and
Geoffrey Zweig and
Kam{-}Fai Wong},
editor = {Mirella Lapata and
Phil Blunsom and
Alexander Koller},
title = {May {I} take your order? {A} Neural Model for Extracting Structured
Information from Conversations},
booktitle = {Proceedings of the 15th Conference of the European Chapter of the
Association for Computational Linguistics, {EACL} 2017, Valencia,
Spain, April 3-7, 2017, Volume 1: Long Papers},
pages = {450--459},
publisher = {Association for Computational Linguistics},
year = {2017},
url = {https://doi.org/10.18653/v1/e17-1043},
doi = {10.18653/V1/E17-1043},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/eacl/WongPZSJ17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/KoPPSK17,
author = {Tom Ko and
Vijayaditya Peddinti and
Daniel Povey and
Michael L. Seltzer and
Sanjeev Khudanpur},
title = {A study on data augmentation of reverberant speech for robust speech
recognition},
booktitle = {2017 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2017, New Orleans, LA, USA, March 5-9, 2017},
pages = {5220--5224},
publisher = {{IEEE}},
year = {2017},
url = {https://doi.org/10.1109/ICASSP.2017.7953152},
doi = {10.1109/ICASSP.2017.7953152},
timestamp = {Wed, 16 Oct 2019 14:14:52 +0200},
biburl = {https://dblp.org/rec/conf/icassp/KoPPSK17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/LiSWZG17,
author = {Jinyu Li and
Michael L. Seltzer and
Xi Wang and
Rui Zhao and
Yifan Gong},
editor = {Francisco Lacerda},
title = {Large-Scale Domain Adaptation via Teacher-Student Learning},
booktitle = {Interspeech 2017, 18th Annual Conference of the International Speech
Communication Association, Stockholm, Sweden, August 20-24, 2017},
pages = {2386--2390},
publisher = {{ISCA}},
year = {2017},
url = {https://doi.org/10.21437/Interspeech.2017-519},
doi = {10.21437/INTERSPEECH.2017-519},
timestamp = {Sun, 06 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/LiSWZG17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@incollection{DBLP:books/sp/17/XiaoWEMLHSCZY17,
author = {Xiong Xiao and
Shinji Watanabe and
Hakan Erdogan and
Michael I. Mandel and
Liang Lu and
John R. Hershey and
Michael L. Seltzer and
Guoguo Chen and
Yu Zhang and
Dong Yu},
editor = {Shinji Watanabe and
Marc Delcroix and
Florian Metze and
John R. Hershey},
title = {Discriminative Beamforming with Phase-Aware Neural Networks for Speech
Enhancement and Recognition},
booktitle = {New Era for Robust Speech Recognition, Exploiting Deep Learning},
pages = {79--104},
publisher = {Springer},
year = {2017},
url = {https://doi.org/10.1007/978-3-319-64680-0\_4},
doi = {10.1007/978-3-319-64680-0\_4},
timestamp = {Sat, 31 Jul 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/books/sp/17/XiaoWEMLHSCZY17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1708-05466,
author = {Jinyu Li and
Michael L. Seltzer and
Xi Wang and
Rui Zhao and
Yifan Gong},
title = {Large-Scale Domain Adaptation via Teacher-Student Learning},
journal = {CoRR},
volume = {abs/1708.05466},
year = {2017},
url = {http://arxiv.org/abs/1708.05466},
eprinttype = {arXiv},
eprint = {1708.05466},
timestamp = {Fri, 07 Oct 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1708-05466.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1711-02207,
author = {Suyoun Kim and
Michael L. Seltzer},
title = {Towards Language-Universal End-to-End Speech Recognition},
journal = {CoRR},
volume = {abs/1711.02207},
year = {2017},
url = {http://arxiv.org/abs/1711.02207},
eprinttype = {arXiv},
eprint = {1711.02207},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1711-02207.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1711-02212,
author = {Suyoun Kim and
Michael L. Seltzer and
Jinyu Li and
Rui Zhao},
title = {Improved training for online end-to-end speech recognition systems},
journal = {CoRR},
volume = {abs/1711.02212},
year = {2017},
url = {http://arxiv.org/abs/1711.02212},
eprinttype = {arXiv},
eprint = {1711.02212},
timestamp = {Fri, 07 Oct 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1711-02212.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/GhahremaniDS16,
author = {Pegah Ghahremani and
Jasha Droppo and
Michael L. Seltzer},
title = {Linearly augmented deep neural network},
booktitle = {2016 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2016, Shanghai, China, March 20-25, 2016},
pages = {5085--5089},
publisher = {{IEEE}},
year = {2016},
url = {https://doi.org/10.1109/ICASSP.2016.7472646},
doi = {10.1109/ICASSP.2016.7472646},
timestamp = {Sun, 25 Oct 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/GhahremaniDS16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/XiaoWELHSCZMY16,
author = {Xiong Xiao and
Shinji Watanabe and
Hakan Erdogan and
Liang Lu and
John R. Hershey and
Michael L. Seltzer and
Guoguo Chen and
Yu Zhang and
Michael I. Mandel and
Dong Yu},
title = {Deep beamforming networks for multi-channel speech recognition},
booktitle = {2016 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2016, Shanghai, China, March 20-25, 2016},
pages = {5745--5749},
publisher = {{IEEE}},
year = {2016},
url = {https://doi.org/10.1109/ICASSP.2016.7472778},
doi = {10.1109/ICASSP.2016.7472778},
timestamp = {Sat, 31 Jul 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/XiaoWELHSCZMY16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/NagamineSM16,
author = {Tasha Nagamine and
Michael L. Seltzer and
Nima Mesgarani},
editor = {Nelson Morgan},
title = {On the Role of Nonlinear Transformations in Deep Neural Network Acoustic
Models},
booktitle = {Interspeech 2016, 17th Annual Conference of the International Speech
Communication Association, San Francisco, CA, USA, September 8-12,
2016},
pages = {803--807},
publisher = {{ISCA}},
year = {2016},
url = {https://doi.org/10.21437/Interspeech.2016-1406},
doi = {10.21437/INTERSPEECH.2016-1406},
timestamp = {Mon, 26 Jun 2023 16:43:56 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/NagamineSM16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/taslp/WengYSD15,
author = {Chao Weng and
Dong Yu and
Michael L. Seltzer and
Jasha Droppo},
title = {Deep Neural Networks for Single-Channel Multi-Talker Speech Recognition},
journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.},
volume = {23},
number = {10},
pages = {1670--1679},
year = {2015},
url = {https://doi.org/10.1109/TASLP.2015.2444659},
doi = {10.1109/TASLP.2015.2444659},
timestamp = {Mon, 26 Oct 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/taslp/WengYSD15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/ZhangYSD15,
author = {Yu Zhang and
Dong Yu and
Michael L. Seltzer and
Jasha Droppo},
title = {Speech recognition with prediction-adaptation-correction recurrent
neural networks},
booktitle = {2015 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2015, South Brisbane, Queensland, Australia,
April 19-24, 2015},
pages = {5004--5008},
publisher = {{IEEE}},
year = {2015},
url = {https://doi.org/10.1109/ICASSP.2015.7178923},
doi = {10.1109/ICASSP.2015.7178923},
timestamp = {Sun, 25 Oct 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/ZhangYSD15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/GiriSDY15,
author = {Ritwik Giri and
Michael L. Seltzer and
Jasha Droppo and
Dong Yu},
title = {Improving speech recognition in reverberation using a room-aware deep
neural network and multi-task learning},
booktitle = {2015 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2015, South Brisbane, Queensland, Australia,
April 19-24, 2015},
pages = {5014--5018},
publisher = {{IEEE}},
year = {2015},
url = {https://doi.org/10.1109/ICASSP.2015.7178925},
doi = {10.1109/ICASSP.2015.7178925},
timestamp = {Sun, 25 Oct 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/GiriSDY15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/NagamineSM15,
author = {Tasha Nagamine and
Michael L. Seltzer and
Nima Mesgarani},
title = {Exploring how deep neural networks form phonemic categories},
booktitle = {{INTERSPEECH} 2015, 16th Annual Conference of the International Speech
Communication Association, Dresden, Germany, September 6-10, 2015},
pages = {1912--1916},
publisher = {{ISCA}},
year = {2015},
url = {https://doi.org/10.21437/Interspeech.2015-422},
doi = {10.21437/INTERSPEECH.2015-422},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/NagamineSM15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/SeoKS14,
author = {Hyunson Seo and
Hong{-}Goo Kang and
Michael L. Seltzer},
title = {Factored adaptation of speaker and environment using orthogonal subspace
transforms},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2014, Florence, Italy, May 4-9, 2014},
pages = {3251--3255},
publisher = {{IEEE}},
year = {2014},
url = {https://doi.org/10.1109/ICASSP.2014.6854201},
doi = {10.1109/ICASSP.2014.6854201},
timestamp = {Wed, 16 Oct 2019 14:14:52 +0200},
biburl = {https://dblp.org/rec/conf/icassp/SeoKS14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/WengYSD14,
author = {Chao Weng and
Dong Yu and
Michael L. Seltzer and
Jasha Droppo},
title = {Single-channel mixed speech recognition using deep neural networks},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2014, Florence, Italy, May 4-9, 2014},
pages = {5632--5636},
publisher = {{IEEE}},
year = {2014},
url = {https://doi.org/10.1109/ICASSP.2014.6854681},
doi = {10.1109/ICASSP.2014.6854681},
timestamp = {Sun, 25 Oct 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/WengYSD14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/HuangSSG14,
author = {Yan Huang and
Malcolm Slaney and
Michael L. Seltzer and
Yifan Gong},
editor = {Haizhou Li and
Helen M. Meng and
Bin Ma and
Engsiong Chng and
Lei Xie},
title = {Towards better performance with heterogeneous training data in acoustic
modeling using deep neural networks},
booktitle = {{INTERSPEECH} 2014, 15th Annual Conference of the International Speech
Communication Association, Singapore, September 14-18, 2014},
pages = {845--849},
publisher = {{ISCA}},
year = {2014},
url = {https://doi.org/10.21437/Interspeech.2014-214},
doi = {10.21437/INTERSPEECH.2014-214},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/HuangSSG14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/SlaneyS14,
author = {Malcolm Slaney and
Michael L. Seltzer},
editor = {Haizhou Li and
Helen M. Meng and
Bin Ma and
Engsiong Chng and
Lei Xie},
title = {The influence of pitch and noise on the discriminability of filterbank
features},
booktitle = {{INTERSPEECH} 2014, 15th Annual Conference of the International Speech
Communication Association, Singapore, September 14-18, 2014},
pages = {2263--2267},
publisher = {{ISCA}},
year = {2014},
url = {https://doi.org/10.21437/Interspeech.2014-251},
doi = {10.21437/INTERSPEECH.2014-251},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/SlaneyS14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/YuESYGKSWDHZRC14,
author = {Dong Yu and
Adam Eversole and
Michael L. Seltzer and
Kaisheng Yao and
Brian Guenter and
Oleksii Kuchaiev and
Frank Seide and
Huaming Wang and
Jasha Droppo and
Zhiheng Huang and
Geoffrey Zweig and
Christopher J. Rossbach and
Jon Currey},
editor = {Haizhou Li and
Helen M. Meng and
Bin Ma and
Engsiong Chng and
Lei Xie},
title = {An introduction to computational networks and the computational network
toolkit (invited talk)},
booktitle = {{INTERSPEECH} 2014, 15th Annual Conference of the International Speech
Communication Association, Singapore, September 14-18, 2014},
publisher = {{ISCA}},
year = {2014},
url = {https://www.isca-speech.org/archive/interspeech\_2014/yu14d\_interspeech.html},
timestamp = {Tue, 27 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/YuESYGKSWDHZRC14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/ThomasSCH13,
author = {Samuel Thomas and
Michael L. Seltzer and
Kenneth Church and
Hynek Hermansky},
title = {Deep neural network features and semi-supervised training for low
resource speech recognition},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2013, Vancouver, BC, Canada, May 26-31, 2013},
pages = {6704--6708},
publisher = {{IEEE}},
year = {2013},
url = {https://doi.org/10.1109/ICASSP.2013.6638959},
doi = {10.1109/ICASSP.2013.6638959},
timestamp = {Mon, 26 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/ThomasSCH13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/SeltzerD13,
author = {Michael L. Seltzer and
Jasha Droppo},
title = {Multi-task learning in deep neural networks for improved phoneme recognition},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2013, Vancouver, BC, Canada, May 26-31, 2013},
pages = {6965--6969},
publisher = {{IEEE}},
year = {2013},
url = {https://doi.org/10.1109/ICASSP.2013.6639012},
doi = {10.1109/ICASSP.2013.6639012},
timestamp = {Sun, 25 Oct 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/SeltzerD13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/SeltzerYW13,
author = {Michael L. Seltzer and
Dong Yu and
Yongqiang Wang},
title = {An investigation of deep neural networks for noise robust speech recognition},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2013, Vancouver, BC, Canada, May 26-31, 2013},
pages = {7398--7402},
publisher = {{IEEE}},
year = {2013},
url = {https://doi.org/10.1109/ICASSP.2013.6639100},
doi = {10.1109/ICASSP.2013.6639100},
timestamp = {Thu, 03 Nov 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/SeltzerYW13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/DengLHYYSSZHWGA13,
author = {Li Deng and
Jinyu Li and
Jui{-}Ting Huang and
Kaisheng Yao and
Dong Yu and
Frank Seide and
Michael L. Seltzer and
Geoffrey Zweig and
Xiaodong He and
Jason D. Williams and
Yifan Gong and
Alex Acero},
title = {Recent advances in deep learning for speech research at Microsoft},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2013, Vancouver, BC, Canada, May 26-31, 2013},
pages = {8604--8608},
publisher = {{IEEE}},
year = {2013},
url = {https://doi.org/10.1109/ICASSP.2013.6639345},
doi = {10.1109/ICASSP.2013.6639345},
timestamp = {Tue, 21 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/DengLHYYSSZHWGA13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:journals/corr/abs-1301-3605,
author = {Dong Yu and
Michael L. Seltzer and
Jinyu Li and
Jui{-}Ting Huang and
Frank Seide},
editor = {Yoshua Bengio and
Yann LeCun},
title = {Feature Learning in Deep Neural Networks - {A} Study on Speech Recognition
Tasks},
booktitle = {1st International Conference on Learning Representations, {ICLR} 2013,
Scottsdale, Arizona, USA, May 2-4, 2013, Conference Track Proceedings},
year = {2013},
url = {http://arxiv.org/abs/1301.3605},
timestamp = {Mon, 03 May 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1301-3605.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/LiSG12,
author = {Jinyu Li and
Michael L. Seltzer and
Yifan Gong},
title = {Improvements to {VTS} feature enhancement},
booktitle = {2012 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2012, Kyoto, Japan, March 25-30, 2012},
pages = {4677--4680},
publisher = {{IEEE}},
year = {2012},
url = {https://doi.org/10.1109/ICASSP.2012.6288962},
doi = {10.1109/ICASSP.2012.6288962},
timestamp = {Tue, 21 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/LiSG12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/SeltzerA12,
author = {Michael L. Seltzer and
Alex Acero},
title = {Factored adaptation using a combination of feature-space and model-space
transforms},
booktitle = {{INTERSPEECH} 2012, 13th Annual Conference of the International Speech
Communication Association, Portland, Oregon, USA, September 9-13,
2012},
pages = {1792--1795},
publisher = {{ISCA}},
year = {2012},
url = {https://doi.org/10.21437/Interspeech.2012-488},
doi = {10.21437/INTERSPEECH.2012-488},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/SeltzerA12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/LiSG12,
author = {Jinyu Li and
Michael L. Seltzer and
Yifan Gong},
title = {Efficient {VTS} Adaptation Using Jacobian Approximation},
booktitle = {{INTERSPEECH} 2012, 13th Annual Conference of the International Speech
Communication Association, Portland, Oregon, USA, September 9-13,
2012},
pages = {1906--1909},
publisher = {{ISCA}},
year = {2012},
url = {https://doi.org/10.21437/Interspeech.2012-517},
doi = {10.21437/INTERSPEECH.2012-517},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/LiSG12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@incollection{DBLP:books/wi/12/Seltzer12,
author = {Michael L. Seltzer},
editor = {Tuomas Virtanen and
Rita Singh and
Bhiksha Raj},
title = {Acoustic Model Training for Robust Speech Recognition},
booktitle = {Techniques for Noise Robustness in Automatic Speech Recognition},
pages = {347--368},
publisher = {Wiley},
year = {2012},
url = {https://doi.org/10.1002/9781118392683.ch13},
doi = {10.1002/9781118392683.CH13},
timestamp = {Thu, 27 Jun 2019 13:28:41 +0200},
biburl = {https://dblp.org/rec/books/wi/12/Seltzer12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/spm/SeltzerJTWY11,
author = {Michael L. Seltzer and
Yun{-}Cheng Ju and
Ivan Tashev and
Ye{-}Yi Wang and
Dong Yu},
title = {In-Car Media Search},
journal = {{IEEE} Signal Process. Mag.},
volume = {28},
number = {4},
pages = {50--60},
year = {2011},
url = {https://doi.org/10.1109/MSP.2011.941065},
doi = {10.1109/MSP.2011.941065},
timestamp = {Thu, 12 Jul 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/spm/SeltzerJTWY11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/asru/SeltzerA11,
author = {Michael L. Seltzer and
Alex Acero},
editor = {David Nahamoo and
Michael Picheny},
title = {Factored adaptation for separable compensation of speaker and environmental
variability},
booktitle = {2011 {IEEE} Workshop on Automatic Speech Recognition {\&} Understanding,
{ASRU} 2011, Waikoloa, HI, USA, December 11-15, 2011},
pages = {146--151},
publisher = {{IEEE}},
year = {2011},
url = {https://doi.org/10.1109/ASRU.2011.6163921},
doi = {10.1109/ASRU.2011.6163921},
timestamp = {Wed, 16 Oct 2019 14:14:51 +0200},
biburl = {https://dblp.org/rec/conf/asru/SeltzerA11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/RibeiroFZS11,
author = {Flavio P. Ribeiro and
Dinei A. F. Flor{\^{e}}ncio and
Cha Zhang and
Michael L. Seltzer},
title = {{CROWDMOS:} An approach for crowdsourcing mean opinion score studies},
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 = {2416--2419},
publisher = {{IEEE}},
year = {2011},
url = {https://doi.org/10.1109/ICASSP.2011.5946971},
doi = {10.1109/ICASSP.2011.5946971},
timestamp = {Fri, 19 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/RibeiroFZS11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/FanSDMA11,
author = {Xing Fan and
Michael L. Seltzer and
Jasha Droppo and
Henrique S. Malvar and
Alex Acero},
title = {Joint encoding of the waveform and speech recognition features using
a transform codec},
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 = {5148--5151},
publisher = {{IEEE}},
year = {2011},
url = {https://doi.org/10.1109/ICASSP.2011.5947516},
doi = {10.1109/ICASSP.2011.5947516},
timestamp = {Sun, 25 Oct 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/FanSDMA11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/YuS11,
author = {Dong Yu and
Michael L. Seltzer},
title = {Improved Bottleneck Features Using Pretrained Deep Neural Networks},
booktitle = {{INTERSPEECH} 2011, 12th Annual Conference of the International Speech
Communication Association, Florence, Italy, August 27-31, 2011},
pages = {237--240},
publisher = {{ISCA}},
year = {2011},
url = {https://doi.org/10.21437/Interspeech.2011-91},
doi = {10.21437/INTERSPEECH.2011-91},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/YuS11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/SeltzerA11,
author = {Michael L. Seltzer and
Alex Acero},
title = {Separating Speaker and Environmental Variability Using Factored Transforms},
booktitle = {{INTERSPEECH} 2011, 12th Annual Conference of the International Speech
Communication Association, Florence, Italy, August 27-31, 2011},
pages = {1097--1100},
publisher = {{ISCA}},
year = {2011},
url = {https://doi.org/10.21437/Interspeech.2011-415},
doi = {10.21437/INTERSPEECH.2011-415},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/SeltzerA11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/taslp/KalinliSDA10,
author = {Ozlem Kalinli and
Michael L. Seltzer and
Jasha Droppo and
Alex Acero},
title = {Noise Adaptive Training for Robust Automatic Speech Recognition},
journal = {{IEEE} Trans. Speech Audio Process.},
volume = {18},
number = {8},
pages = {1889--1901},
year = {2010},
url = {https://doi.org/10.1109/TASL.2010.2040522},
doi = {10.1109/TASL.2010.2040522},
timestamp = {Mon, 26 Oct 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/taslp/KalinliSDA10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/SeltzerAK10,
author = {Michael L. Seltzer and
Alex Acero and
Kaustubh Kalgaonkar},
title = {Acoustic model adaptation via Linear Spline Interpolation for robust
speech recognition},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing, {ICASSP} 2010, 14-19 March 2010, Sheraton Dallas
Hotel, Dallas, Texas, {USA}},
pages = {4550--4553},
publisher = {{IEEE}},
year = {2010},
url = {https://doi.org/10.1109/ICASSP.2010.5495581},
doi = {10.1109/ICASSP.2010.5495581},
timestamp = {Fri, 19 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/SeltzerAK10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/SeltzerA10,
author = {Michael L. Seltzer and
Alex Acero},
editor = {Takao Kobayashi and
Keikichi Hirose and
Satoshi Nakamura},
title = {{HMM} adaptation using linear spline interpolation with integrated
spline parameter training for robust speech recognition},
booktitle = {{INTERSPEECH} 2010, 11th Annual Conference of the International Speech
Communication Association, Makuhari, Chiba, Japan, September 26-30,
2010},
pages = {1664--1667},
publisher = {{ISCA}},
year = {2010},
url = {https://doi.org/10.21437/Interspeech.2010-480},
doi = {10.21437/INTERSPEECH.2010-480},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/SeltzerA10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/DengSYAMH10,
author = {Li Deng and
Michael L. Seltzer and
Dong Yu and
Alex Acero and
Abdel{-}rahman Mohamed and
Geoffrey E. Hinton},
editor = {Takao Kobayashi and
Keikichi Hirose and
Satoshi Nakamura},
title = {Binary coding of speech spectrograms using a deep auto-encoder},
booktitle = {{INTERSPEECH} 2010, 11th Annual Conference of the International Speech
Communication Association, Makuhari, Chiba, Japan, September 26-30,
2010},
pages = {1692--1695},
publisher = {{ISCA}},
year = {2010},
url = {https://doi.org/10.21437/Interspeech.2010-487},
doi = {10.21437/INTERSPEECH.2010-487},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/DengSYAMH10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/asru/KalgaonkarSA09,
author = {Kaustubh Kalgaonkar and
Michael L. Seltzer and
Alex Acero},
title = {Noise robust model adaptation using linear spline interpolation},
booktitle = {2009 {IEEE} Workshop on Automatic Speech Recognition {\&} Understanding,
{ASRU} 2009, Merano/Meran, Italy, December 13-17, 2009},
pages = {199--204},
publisher = {{IEEE}},
year = {2009},
url = {https://doi.org/10.1109/ASRU.2009.5373430},
doi = {10.1109/ASRU.2009.5373430},
timestamp = {Wed, 16 Oct 2019 14:14:51 +0200},
biburl = {https://dblp.org/rec/conf/asru/KalgaonkarSA09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/SeltzerZ09,
author = {Michael L. Seltzer and
Lei Zhang},
title = {The data deluge: Challenges and opportunities of unlimited data in
statistical signal processing},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing, {ICASSP} 2009, 19-24 April 2009, Taipei, Taiwan},
pages = {3701--3704},
publisher = {{IEEE}},
year = {2009},
url = {https://doi.org/10.1109/ICASSP.2009.4960430},
doi = {10.1109/ICASSP.2009.4960430},
timestamp = {Thu, 23 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/SeltzerZ09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/KalinliSA09,
author = {Ozlem Kalinli and
Michael L. Seltzer and
Alex Acero},
title = {Noise adaptive training using a vector taylor series approach for
noise robust automatic speech recognition},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing, {ICASSP} 2009, 19-24 April 2009, Taipei, Taiwan},
pages = {3825--3828},
publisher = {{IEEE}},
year = {2009},
url = {https://doi.org/10.1109/ICASSP.2009.4960461},
doi = {10.1109/ICASSP.2009.4960461},
timestamp = {Thu, 23 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/KalinliSA09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/SongWJSTA09,
author = {Young{-}In Song and
Ye{-}Yi Wang and
Yun{-}Cheng Ju and
Michael L. Seltzer and
Ivan Tashev and
Alex Acero},
title = {Voice search of structured media data},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing, {ICASSP} 2009, 19-24 April 2009, Taipei, Taiwan},
pages = {3941--3944},
publisher = {{IEEE}},
year = {2009},
url = {https://doi.org/10.1109/ICASSP.2009.4960490},
doi = {10.1109/ICASSP.2009.4960490},
timestamp = {Thu, 23 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/SongWJSTA09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/JuST09,
author = {Yun{-}Cheng Ju and
Michael L. Seltzer and
Ivan Tashev},
title = {Improving perceived accuracy for in-car media search},
booktitle = {{INTERSPEECH} 2009, 10th Annual Conference of the International Speech
Communication Association, Brighton, United Kingdom, September 6-10,
2009},
pages = {979--982},
publisher = {{ISCA}},
year = {2009},
url = {https://doi.org/10.21437/Interspeech.2009-291},
doi = {10.21437/INTERSPEECH.2009-291},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/JuST09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/TashevDSA08,
author = {Ivan Tashev and
Jasha Droppo and
Michael L. Seltzer and
Alex Acero},
title = {Robust design of wideband loudspeaker arrays},
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 = {381--384},
publisher = {{IEEE}},
year = {2008},
url = {https://doi.org/10.1109/ICASSP.2008.4517626},
doi = {10.1109/ICASSP.2008.4517626},
timestamp = {Sun, 25 Oct 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/TashevDSA08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/TaylorSA08,
author = {Graham W. Taylor and
Michael L. Seltzer and
Alex Acero},
title = {Maximum a posteriori {ICA:} Applying prior knowledge to the separation
of acoustic sources},
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 = {1821--1824},
publisher = {{IEEE}},
year = {2008},
url = {https://doi.org/10.1109/ICASSP.2008.4517986},
doi = {10.1109/ICASSP.2008.4517986},
timestamp = {Fri, 19 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/TaylorSA08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/DroppoSAC08,
author = {Jasha Droppo and
Michael L. Seltzer and
Alex Acero and
Yu{-}Hsiang Bosco Chiu},
title = {Towards a non-parametric acoustic model: an acoustic decision tree
for observation probability calculation},
booktitle = {{INTERSPEECH} 2008, 9th Annual Conference of the International Speech
Communication Association, Brisbane, Australia, September 22-26, 2008},
pages = {289--292},
publisher = {{ISCA}},
year = {2008},
url = {https://doi.org/10.21437/Interspeech.2008-105},
doi = {10.21437/INTERSPEECH.2008-105},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/DroppoSAC08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/spl/SubramanyaSA07,
author = {Amarnag Subramanya and
Michael L. Seltzer and
Alejandro Acero},
title = {Automatic Removal of Typed Keystrokes From Speech Signals},
journal = {{IEEE} Signal Process. Lett.},
volume = {14},
number = {5},
pages = {363--366},
year = {2007},
url = {https://doi.org/10.1109/LSP.2006.888091},
doi = {10.1109/LSP.2006.888091},
timestamp = {Sun, 28 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/spl/SubramanyaSA07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/taslp/SeltzerA07,
author = {Michael L. Seltzer and
Alex Acero},
title = {Training Wideband Acoustic Models Using Mixed-Bandwidth Training Data
for Speech Recognition},
journal = {{IEEE} Trans. Speech Audio Process.},
volume = {15},
number = {1},
pages = {235--245},
year = {2007},
url = {https://doi.org/10.1109/TASL.2006.876774},
doi = {10.1109/TASL.2006.876774},
timestamp = {Sun, 17 May 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/taslp/SeltzerA07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/SeltzerTA07,
author = {Michael L. Seltzer and
Ivan Tashev and
Alex Acero},
title = {Microphone Array Post-Filter using Incremental Bayes Learning to Track
the Spatial Distributions of Speech and Noise},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing, {ICASSP} 2007, Honolulu, Hawaii, USA, April
15-20, 2007},
pages = {29--32},
publisher = {{IEEE}},
year = {2007},
url = {https://doi.org/10.1109/ICASSP.2007.366608},
doi = {10.1109/ICASSP.2007.366608},
timestamp = {Mon, 22 Jun 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/SeltzerTA07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/SeltzerJTA07,
author = {Michael L. Seltzer and
Yun{-}Cheng Ju and
Ivan Tashev and
Alex Acero},
title = {Robust location understanding in spoken dialog systems using intersections},
booktitle = {{INTERSPEECH} 2007, 8th Annual Conference of the International Speech
Communication Association, Antwerp, Belgium, August 27-31, 2007},
pages = {2813--2816},
publisher = {{ISCA}},
year = {2007},
url = {https://doi.org/10.21437/Interspeech.2007-725},
doi = {10.21437/INTERSPEECH.2007-725},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/SeltzerJTA07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sigdial/TashevSJYA07,
author = {Ivan Tashev and
Michael L. Seltzer and
Yun{-}Cheng Ju and
Dong Yu and
Alex Acero},
editor = {Harry Bunt and
Simon Keizer and
Tim Paek},
title = {Commute {UX:} Telephone Dialog System for Location-based Services},
booktitle = {Proceedings of the 8th SIGdial Workshop on Discourse and Dialogue,
SIGdial 2007, Antwerp, Belgium, September 1-2, 2007},
pages = {87--94},
publisher = {Association for Computational Linguistics},
year = {2007},
url = {https://aclanthology.org/2007.sigdial-1.18/},
timestamp = {Fri, 06 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/sigdial/TashevSJYA07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/taslp/SeltzerS06,
author = {Michael L. Seltzer and
Richard M. Stern},
title = {Subband Likelihood-Maximizing Beamforming for Speech Recognition in
Reverberant Environments},
journal = {{IEEE} Trans. Speech Audio Process.},
volume = {14},
number = {6},
pages = {2109--2121},
year = {2006},
url = {https://doi.org/10.1109/TASL.2006.872614},
doi = {10.1109/TASL.2006.872614},
timestamp = {Sun, 17 May 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/taslp/SeltzerS06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/SubramanyaSA06,
author = {Amarnag Subramanya and
Michael L. Seltzer and
Alex Acero},
title = {Automatic removal of typed keystrokes from speech signals},
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.2006-72},
doi = {10.21437/INTERSPEECH.2006-72},
timestamp = {Thu, 22 Jun 2023 16:42:16 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/SubramanyaSA06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/SeltzerA05,
author = {Michael L. Seltzer and
Alex Acero},
title = {Training Wideband Acoustic Models using Mixed-Bandwidth Training Data
via Feature Bandwidth Extension},
booktitle = {2005 {IEEE} International Conference on Acoustics, Speech, and Signal
Processing, {ICASSP} '05, Philadelphia, Pennsylvania, USA, March 18-23,
2005},
pages = {921--924},
publisher = {{IEEE}},
year = {2005},
url = {https://doi.org/10.1109/ICASSP.2005.1415265},
doi = {10.1109/ICASSP.2005.1415265},
timestamp = {Mon, 22 Jun 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/SeltzerA05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/SeltzerAD05,
author = {Michael L. Seltzer and
Alex Acero and
Jasha Droppo},
title = {Robust bandwidth extension of noise-corrupted narrowband speech},
booktitle = {{INTERSPEECH} 2005 - Eurospeech, 9th European Conference on Speech
Communication and Technology, Lisbon, Portugal, September 4-8, 2005},
pages = {1509--1512},
publisher = {{ISCA}},
year = {2005},
url = {https://doi.org/10.21437/Interspeech.2005-529},
doi = {10.21437/INTERSPEECH.2005-529},
timestamp = {Thu, 22 Jun 2023 16:42:16 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/SeltzerAD05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@incollection{DBLP:books/sp/05/RajSR05,
author = {Bhiksha Raj and
Michael L. Seltzer and
Manuel Jesus Reyes{-}Gomez},
editor = {Pierre L. Divenyi},
title = {Speech Recognizer Based Maximum Likelihood Beamforming},
booktitle = {Speech Separation by Humans and Machines},
pages = {65--82},
publisher = {Springer},
year = {2005},
url = {https://doi.org/10.1007/0-387-22794-6\_6},
doi = {10.1007/0-387-22794-6\_6},
timestamp = {Thu, 25 Jul 2019 16:54:17 +0200},
biburl = {https://dblp.org/rec/books/sp/05/RajSR05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/speech/RajSS04,
author = {Bhiksha Raj and
Michael L. Seltzer and
Richard M. Stern},
title = {Reconstruction of missing features for robust speech recognition},
journal = {Speech Commun.},
volume = {43},
number = {4},
pages = {275--296},
year = {2004},
url = {https://doi.org/10.1016/j.specom.2004.03.007},
doi = {10.1016/J.SPECOM.2004.03.007},
timestamp = {Sat, 22 Feb 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/speech/RajSS04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/speech/SeltzerRS04,
author = {Michael L. Seltzer and
Bhiksha Raj and
Richard M. Stern},
title = {A Bayesian classifier for spectrographic mask estimation for missing
feature speech recognition},
journal = {Speech Commun.},
volume = {43},
number = {4},
pages = {379--393},
year = {2004},
url = {https://doi.org/10.1016/j.specom.2004.03.006},
doi = {10.1016/J.SPECOM.2004.03.006},
timestamp = {Sat, 22 Feb 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/speech/SeltzerRS04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/taslp/SeltzerRS04,
author = {Michael L. Seltzer and
Bhiksha Raj and
Richard M. Stern},
title = {Likelihood-maximizing beamforming for robust hands-free speech recognition},
journal = {{IEEE} Trans. Speech Audio Process.},
volume = {12},
number = {5},
pages = {489--498},
year = {2004},
url = {https://doi.org/10.1109/TSA.2004.832988},
doi = {10.1109/TSA.2004.832988},
timestamp = {Sun, 17 May 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/taslp/SeltzerRS04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/SeltzerS04,
author = {Michael L. Seltzer and
Richard M. Stern},
title = {Parameter sharing in subband likelihood-maximizing beamforming for
speech recognition using microphone arrays},
booktitle = {2004 {IEEE} International Conference on Acoustics, Speech, and Signal
Processing, {ICASSP} 2004, Montreal, Quebec, Canada, May 17-21, 2004},
pages = {881--884},
publisher = {{IEEE}},
year = {2004},
url = {https://doi.org/10.1109/ICASSP.2004.1326127},
doi = {10.1109/ICASSP.2004.1326127},
timestamp = {Mon, 22 Jun 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/SeltzerS04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/spl/SeltzerR03,
author = {Michael L. Seltzer and
Bhiksha Raj},
title = {Speech-recognizer-based filter optimization for microphone array processing},
journal = {{IEEE} Signal Process. Lett.},
volume = {10},
number = {3},
pages = {69--71},
year = {2003},
url = {https://doi.org/10.1109/LSP.2002.807877},
doi = {10.1109/LSP.2002.807877},
timestamp = {Mon, 01 Mar 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/spl/SeltzerR03.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/SeltzerS03,
author = {Michael L. Seltzer and
Richard M. Stern},
title = {Subband parameter optimization of microphone arrays for speech recognition
in reverberant environments},
booktitle = {2003 {IEEE} International Conference on Acoustics, Speech, and Signal
Processing, {ICASSP} '03, Hong Kong, April 6-10, 2003},
pages = {408--411},
publisher = {{IEEE}},
year = {2003},
url = {https://doi.org/10.1109/ICASSP.2003.1198804},
doi = {10.1109/ICASSP.2003.1198804},
timestamp = {Mon, 22 Jun 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/SeltzerS03.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/SeltzerDA03,
author = {Michael L. Seltzer and
Jasha Droppo and
Alex Acero},
title = {A harmonic-model-based front end for robust speech recognition},
booktitle = {8th European Conference on Speech Communication and Technology, {EUROSPEECH}
2003 - {INTERSPEECH} 2003, Geneva, Switzerland, September 1-4, 2003},
pages = {1277--1280},
publisher = {{ISCA}},
year = {2003},
url = {https://doi.org/10.21437/Eurospeech.2003-406},
doi = {10.21437/EUROSPEECH.2003-406},
timestamp = {Thu, 22 Jun 2023 16:42:17 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/SeltzerDA03.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/SeltzerRS02,
author = {Michael L. Seltzer and
Bhiksha Raj and
Richard M. Stern},
title = {Speech recognizer-based microphone array processing for robust hands-free
speech recognition},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing, {ICASSP} 2002, May 13-17 2002, Orlando, Florida,
{USA}},
pages = {897--900},
publisher = {{IEEE}},
year = {2002},
url = {https://doi.org/10.1109/ICASSP.2002.5743884},
doi = {10.1109/ICASSP.2002.5743884},
timestamp = {Wed, 16 Oct 2019 14:14:52 +0200},
biburl = {https://dblp.org/rec/conf/icassp/SeltzerRS02.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/SinghSRS01,
author = {Rita Singh and
Michael L. Seltzer and
Bhiksha Raj and
Richard M. Stern},
title = {Speech in Noisy Environments: robust automatic segmentation, feature
extraction, and hypothesis combination},
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 = {273--276},
publisher = {{IEEE}},
year = {2001},
url = {https://doi.org/10.1109/ICASSP.2001.940820},
doi = {10.1109/ICASSP.2001.940820},
timestamp = {Thu, 23 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/SinghSRS01.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/SeltzerR01,
author = {Michael L. Seltzer and
Bhiksha Raj},
editor = {Paul Dalsgaard and
B{\o}rge Lindberg and
Henrik Benner and
Zheng{-}Hua Tan},
title = {Calibration of microphone arrays for improved speech recognition},
booktitle = {{EUROSPEECH} 2001 Scandinavia, 7th European Conference on Speech Communication
and Technology, 2nd {INTERSPEECH} Event, Aalborg, Denmark, September
3-7, 2001},
pages = {1005--1008},
publisher = {{ISCA}},
year = {2001},
url = {https://doi.org/10.21437/Eurospeech.2001-289},
doi = {10.21437/EUROSPEECH.2001-289},
timestamp = {Thu, 22 Jun 2023 16:42:18 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/SeltzerR01.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/RajSS00,
author = {Bhiksha Raj and
Michael L. Seltzer and
Richard M. Stern},
title = {Reconstruction of damaged spectrographic features for robust speech
recognition},
booktitle = {Sixth International Conference on Spoken Language Processing, {ICSLP}
2000 / {INTERSPEECH} 2000, Beijing, China, October 16-20, 2000},
pages = {357--360},
publisher = {{ISCA}},
year = {2000},
url = {https://doi.org/10.21437/ICSLP.2000-89},
doi = {10.21437/ICSLP.2000-89},
timestamp = {Thu, 22 Jun 2023 16:42:19 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/RajSS00.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/SeltzerRS00,
author = {Michael L. Seltzer and
Bhiksha Raj and
Richard M. Stern},
title = {Classifier-based mask estimation for missing feature methods of robust
speech recognition},
booktitle = {Sixth International Conference on Spoken Language Processing, {ICSLP}
2000 / {INTERSPEECH} 2000, Beijing, China, October 16-20, 2000},
pages = {538--541},
publisher = {{ISCA}},
year = {2000},
url = {https://doi.org/10.21437/ICSLP.2000-591},
doi = {10.21437/ICSLP.2000-591},
timestamp = {Thu, 22 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/SeltzerRS00.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
a service of 
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
last updated on 2024-04-07 22:28 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:
