default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDBibTeX records: Daniel Povey
@inproceedings{DBLP:conf/coling/HuangYTLRGIEYPK24,
author = {Ruizhe Huang and
Mahsa Yarmohammadi and
Jan Trmal and
Jing Liu and
Desh Raj and
Leibny Paola Garc{\'{\i}}a and
Alexei V. Ivanov and
Patrick Ehlen and
Mingzhi Yu and
Dan Povey and
Sanjeev Khudanpur},
editor = {Nicoletta Calzolari and
Min{-}Yen Kan and
V{\'{e}}ronique Hoste and
Alessandro Lenci and
Sakriani Sakti and
Nianwen Xue},
title = {ConEC: Earnings Call Dataset with Real-world Contexts for Benchmarking
Contextual Speech Recognition},
booktitle = {Proceedings of the 2024 Joint International Conference on Computational
Linguistics, Language Resources and Evaluation, {LREC/COLING} 2024,
20-25 May, 2024, Torino, Italy},
pages = {3700--3706},
publisher = {{ELRA} and {ICCL}},
year = {2024},
url = {https://aclanthology.org/2024.lrec-main.328},
timestamp = {Wed, 12 Jun 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/coling/HuangYTLRGIEYPK24.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/YangSDM0P024,
author = {Yifan Yang and
Feiyu Shen and
Chenpeng Du and
Ziyang Ma and
Kai Yu and
Daniel Povey and
Xie Chen},
title = {Towards Universal Speech Discrete Tokens: {A} Case Study for {ASR}
and {TTS}},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2024, Seoul, Republic of Korea, April 14-19, 2024},
pages = {10401--10405},
publisher = {{IEEE}},
year = {2024},
url = {https://doi.org/10.1109/ICASSP48485.2024.10447751},
doi = {10.1109/ICASSP48485.2024.10447751},
timestamp = {Tue, 06 Aug 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/YangSDM0P024.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/YangKYYGKLP24,
author = {Xiaoyu Yang and
Wei Kang and
Zengwei Yao and
Yifan Yang and
Liyong Guo and
Fangjun Kuang and
Long Lin and
Daniel Povey},
title = {PromptASR for Contextualized {ASR} with Controllable Style},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2024, Seoul, Republic of Korea, April 14-19, 2024},
pages = {10536--10540},
publisher = {{IEEE}},
year = {2024},
url = {https://doi.org/10.1109/ICASSP48485.2024.10448264},
doi = {10.1109/ICASSP48485.2024.10448264},
timestamp = {Wed, 14 Aug 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/YangKYYGKLP24.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/KangYYKYGLP24,
author = {Wei Kang and
Xiaoyu Yang and
Zengwei Yao and
Fangjun Kuang and
Yifan Yang and
Liyong Guo and
Long Lin and
Daniel Povey},
title = {Libriheavy: {A} 50, 000 Hours {ASR} Corpus with Punctuation Casing
and Context},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2024, Seoul, Republic of Korea, April 14-19, 2024},
pages = {10991--10995},
publisher = {{IEEE}},
year = {2024},
url = {https://doi.org/10.1109/ICASSP48485.2024.10447120},
doi = {10.1109/ICASSP48485.2024.10447120},
timestamp = {Tue, 13 Aug 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/KangYYKYGLP24.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/Huang0NSHHMPW0P24,
author = {Ruizhe Huang and
Xiaohui Zhang and
Zhaoheng Ni and
Li Sun and
Moto Hira and
Jeff Hwang and
Vimal Manohar and
Vineel Pratap and
Matthew Wiesner and
Shinji Watanabe and
Daniel Povey and
Sanjeev Khudanpur},
title = {Less Peaky and More Accurate {CTC} Forced Alignment by Label Priors},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2024, Seoul, Republic of Korea, April 14-19, 2024},
pages = {11831--11835},
publisher = {{IEEE}},
year = {2024},
url = {https://doi.org/10.1109/ICASSP48485.2024.10446111},
doi = {10.1109/ICASSP48485.2024.10446111},
timestamp = {Wed, 07 Aug 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/Huang0NSHHMPW0P24.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/YaoGY0KYJLP24,
author = {Zengwei Yao and
Liyong Guo and
Xiaoyu Yang and
Wei Kang and
Fangjun Kuang and
Yifan Yang and
Zengrui Jin and
Long Lin and
Daniel Povey},
title = {Zipformer: {A} faster and better encoder for automatic speech recognition},
booktitle = {The Twelfth International Conference on Learning Representations,
{ICLR} 2024, Vienna, Austria, May 7-11, 2024},
publisher = {OpenReview.net},
year = {2024},
url = {https://openreview.net/forum?id=9WD9KwssyT},
timestamp = {Mon, 29 Jul 2024 16:19:40 +0200},
biburl = {https://dblp.org/rec/conf/iclr/YaoGY0KYJLP24.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/odyssey/RajWM0PK24,
author = {Desh Raj and
Matthew Wiesner and
Matthew Maciejewski and
Paola Garc{\'{\i}}a and
Daniel Povey and
Sanjeev Khudanpur},
editor = {Najim Dehak and
Patrick Cardinal},
title = {On Speaker Attribution with {SURT}},
booktitle = {Odyssey 2024: The Speaker and Language Recognition Workshop, Quebec
City, Canada, June 18-21, 2024},
pages = {91--98},
publisher = {{ISCA}},
year = {2024},
url = {https://doi.org/10.21437/odyssey.2024-14},
doi = {10.21437/ODYSSEY.2024-14},
timestamp = {Wed, 31 Jul 2024 15:08:41 +0200},
biburl = {https://dblp.org/rec/conf/odyssey/RajWM0PK24.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2401-15676,
author = {Desh Raj and
Matthew Wiesner and
Matthew Maciejewski and
Leibny Paola Garc{\'{\i}}a{-}Perera and
Daniel Povey and
Sanjeev Khudanpur},
title = {On Speaker Attribution with {SURT}},
journal = {CoRR},
volume = {abs/2401.15676},
year = {2024},
url = {https://doi.org/10.48550/arXiv.2401.15676},
doi = {10.48550/ARXIV.2401.15676},
eprinttype = {arXiv},
eprint = {2401.15676},
timestamp = {Thu, 08 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2401-15676.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2406-02560,
author = {Ruizhe Huang and
Xiaohui Zhang and
Zhaoheng Ni and
Li Sun and
Moto Hira and
Jeff Hwang and
Vimal Manohar and
Vineel Pratap and
Matthew Wiesner and
Shinji Watanabe and
Daniel Povey and
Sanjeev Khudanpur},
title = {Less Peaky and More Accurate {CTC} Forced Alignment by Label Priors},
journal = {CoRR},
volume = {abs/2406.02560},
year = {2024},
url = {https://doi.org/10.48550/arXiv.2406.02560},
doi = {10.48550/ARXIV.2406.02560},
eprinttype = {arXiv},
eprint = {2406.02560},
timestamp = {Sun, 04 Aug 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2406-02560.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2406-06571,
author = {Quandong Wang and
Yuxuan Yuan and
Xiaoyu Yang and
Ruike Zhang and
Kang Zhao and
Wei Liu and
Jian Luan and
Daniel Povey and
Bin Wang},
title = {{SUBLLM:} {A} Novel Efficient Architecture with Token Sequence Subsampling
for {LLM}},
journal = {CoRR},
volume = {abs/2406.06571},
year = {2024},
url = {https://doi.org/10.48550/arXiv.2406.06571},
doi = {10.48550/ARXIV.2406.06571},
eprinttype = {arXiv},
eprint = {2406.06571},
timestamp = {Tue, 13 Aug 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2406-06571.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2407-10303,
author = {Ruizhe Huang and
Mahsa Yarmohammadi and
Sanjeev Khudanpur and
Daniel Povey},
title = {Improving Neural Biasing for Contextual Speech Recognition by Early
Context Injection and Text Perturbation},
journal = {CoRR},
volume = {abs/2407.10303},
year = {2024},
url = {https://doi.org/10.48550/arXiv.2407.10303},
doi = {10.48550/ARXIV.2407.10303},
eprinttype = {arXiv},
eprint = {2407.10303},
timestamp = {Sat, 24 Aug 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2407-10303.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/taslp/ZhuGCPZY23,
author = {Han Zhu and
Dongji Gao and
Gaofeng Cheng and
Daniel Povey and
Pengyuan Zhang and
Yonghong Yan},
title = {Alternative Pseudo-Labeling for Semi-Supervised Automatic Speech Recognition},
journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.},
volume = {31},
pages = {3320--3330},
year = {2023},
url = {https://doi.org/10.1109/TASLP.2023.3306709},
doi = {10.1109/TASLP.2023.3306709},
timestamp = {Mon, 03 Jun 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/taslp/ZhuGCPZY23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/taslp/RajPK23,
author = {Desh Raj and
Daniel Povey and
Sanjeev Khudanpur},
title = {{SURT} 2.0: Advances in Transducer-Based Multi-Talker Speech Recognition},
journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.},
volume = {31},
pages = {3800--3813},
year = {2023},
url = {https://doi.org/10.1109/TASLP.2023.3318398},
doi = {10.1109/TASLP.2023.3318398},
timestamp = {Thu, 09 Nov 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/taslp/RajPK23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/asru/GaoXRGPK23,
author = {Dongji Gao and
Hainan Xu and
Desh Raj and
Leibny Paola Garc{\'{\i}}a{-}Perera and
Daniel Povey and
Sanjeev Khudanpur},
title = {Learning From Flawed Data: Weakly Supervised Automatic Speech Recognition},
booktitle = {{IEEE} Automatic Speech Recognition and Understanding Workshop, {ASRU}
2023, Taipei, Taiwan, December 16-20, 2023},
pages = {1--8},
publisher = {{IEEE}},
year = {2023},
url = {https://doi.org/10.1109/ASRU57964.2023.10389684},
doi = {10.1109/ASRU57964.2023.10389684},
timestamp = {Tue, 13 Feb 2024 21:21:14 +0100},
biburl = {https://dblp.org/rec/conf/asru/GaoXRGPK23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/GuoYWKYCKKLLZP23,
author = {Liyong Guo and
Xiaoyu Yang and
Quandong Wang and
Yuxiang Kong and
Zengwei Yao and
Fan Cui and
Fangjun Kuang and
Wei Kang and
Long Lin and
Mingshuang Luo and
Piotr Zelasko and
Daniel Povey},
title = {Predicting Multi-Codebook Vector Quantization Indexes for Knowledge
Distillation},
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/ICASSP49357.2023.10095268},
doi = {10.1109/ICASSP49357.2023.10095268},
timestamp = {Sun, 05 Nov 2023 16:51:21 +0100},
biburl = {https://dblp.org/rec/conf/icassp/GuoYWKYCKKLLZP23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/HuangWGPTK23,
author = {Ruizhe Huang and
Matthew Wiesner and
Leibny Paola Garc{\'{\i}}a{-}Perera and
Daniel Povey and
Jan Trmal and
Sanjeev Khudanpur},
title = {Building Keyword Search System from End-To-End Asr Systems},
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/ICASSP49357.2023.10097249},
doi = {10.1109/ICASSP49357.2023.10097249},
timestamp = {Sun, 05 Nov 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/HuangWGPTK23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/KangGKLLYYZP23,
author = {Wei Kang and
Liyong Guo and
Fangjun Kuang and
Long Lin and
Mingshuang Luo and
Zengwei Yao and
Xiaoyu Yang and
Piotr Zelasko and
Daniel Povey},
title = {Fast and Parallel Decoding for Transducer},
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/ICASSP49357.2023.10094567},
doi = {10.1109/ICASSP49357.2023.10094567},
timestamp = {Sun, 05 Nov 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/KangGKLLYYZP23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/KangYKGYLZP23,
author = {Wei Kang and
Zengwei Yao and
Fangjun Kuang and
Liyong Guo and
Xiaoyu Yang and
Long Lin and
Piotr Zelasko and
Daniel Povey},
title = {Delay-Penalized Transducer for Low-Latency Streaming {ASR}},
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/ICASSP49357.2023.10096378},
doi = {10.1109/ICASSP49357.2023.10096378},
timestamp = {Sun, 05 Nov 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/KangYKGYLZP23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/GaoWXGPK23,
author = {Dongji Gao and
Matthew Wiesner and
Hainan Xu and
Leibny Paola Garc{\'{\i}}a and
Daniel Povey and
Sanjeev Khudanpur},
editor = {Naomi Harte and
Julie Carson{-}Berndsen and
Gareth Jones},
title = {Bypass Temporal Classification: Weakly Supervised Automatic Speech
Recognition with Imperfect Transcripts},
booktitle = {24th Annual Conference of the International Speech Communication Association,
Interspeech 2023, Dublin, Ireland, August 20-24, 2023},
pages = {924--928},
publisher = {{ISCA}},
year = {2023},
url = {https://doi.org/10.21437/Interspeech.2023-2258},
doi = {10.21437/INTERSPEECH.2023-2258},
timestamp = {Fri, 14 Jun 2024 14:12:12 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/GaoWXGPK23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/Yao0KGYYLP23,
author = {Zengwei Yao and
Wei Kang and
Fangjun Kuang and
Liyong Guo and
Xiaoyu Yang and
Yifan Yang and
Long Lin and
Daniel Povey},
editor = {Naomi Harte and
Julie Carson{-}Berndsen and
Gareth Jones},
title = {Delay-penalized {CTC} Implemented Based on Finite State Transducer},
booktitle = {24th Annual Conference of the International Speech Communication Association,
Interspeech 2023, Dublin, Ireland, August 20-24, 2023},
pages = {1329--1333},
publisher = {{ISCA}},
year = {2023},
url = {https://doi.org/10.21437/Interspeech.2023-2508},
doi = {10.21437/INTERSPEECH.2023-2508},
timestamp = {Fri, 14 Jun 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/Yao0KGYYLP23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/RajPK23,
author = {Desh Raj and
Daniel Povey and
Sanjeev Khudanpur},
editor = {Naomi Harte and
Julie Carson{-}Berndsen and
Gareth Jones},
title = {GPU-accelerated Guided Source Separation for Meeting Transcription},
booktitle = {24th Annual Conference of the International Speech Communication Association,
Interspeech 2023, Dublin, Ireland, August 20-24, 2023},
pages = {3507--3511},
publisher = {{ISCA}},
year = {2023},
url = {https://doi.org/10.21437/Interspeech.2023-42},
doi = {10.21437/INTERSPEECH.2023-42},
timestamp = {Sun, 04 Aug 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/RajPK23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/YangYGY0KL0P23,
author = {Yifan Yang and
Xiaoyu Yang and
Liyong Guo and
Zengwei Yao and
Wei Kang and
Fangjun Kuang and
Long Lin and
Xie Chen and
Daniel Povey},
editor = {Naomi Harte and
Julie Carson{-}Berndsen and
Gareth Jones},
title = {Blank-regularized {CTC} for Frame Skipping in Neural Transducer},
booktitle = {24th Annual Conference of the International Speech Communication Association,
Interspeech 2023, Dublin, Ireland, August 20-24, 2023},
pages = {4409--4413},
publisher = {{ISCA}},
year = {2023},
url = {https://doi.org/10.21437/Interspeech.2023-759},
doi = {10.21437/INTERSPEECH.2023-759},
timestamp = {Fri, 14 Jun 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/YangYGY0KL0P23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2305-11558,
author = {Yifan Yang and
Xiaoyu Yang and
Liyong Guo and
Zengwei Yao and
Wei Kang and
Fangjun Kuang and
Long Lin and
Xie Chen and
Daniel Povey},
title = {Blank-regularized {CTC} for Frame Skipping in Neural Transducer},
journal = {CoRR},
volume = {abs/2305.11558},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2305.11558},
doi = {10.48550/ARXIV.2305.11558},
eprinttype = {arXiv},
eprint = {2305.11558},
timestamp = {Wed, 20 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2305-11558.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2306-01031,
author = {Dongji Gao and
Matthew Wiesner and
Hainan Xu and
Leibny Paola Garc{\'{\i}}a and
Daniel Povey and
Sanjeev Khudanpur},
title = {Bypass Temporal Classification: Weakly Supervised Automatic Speech
Recognition with Imperfect Transcripts},
journal = {CoRR},
volume = {abs/2306.01031},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2306.01031},
doi = {10.48550/ARXIV.2306.01031},
eprinttype = {arXiv},
eprint = {2306.01031},
timestamp = {Sat, 09 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2306-01031.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2306-10559,
author = {Desh Raj and
Daniel Povey and
Sanjeev Khudanpur},
title = {{SURT} 2.0: Advances in Transducer-based Multi-talker Speech Recognition},
journal = {CoRR},
volume = {abs/2306.10559},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2306.10559},
doi = {10.48550/ARXIV.2306.10559},
eprinttype = {arXiv},
eprint = {2306.10559},
timestamp = {Mon, 05 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2306-10559.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2308-06547,
author = {Han Zhu and
Dongji Gao and
Gaofeng Cheng and
Daniel Povey and
Pengyuan Zhang and
Yonghong Yan},
title = {Alternative Pseudo-Labeling for Semi-Supervised Automatic Speech Recognition},
journal = {CoRR},
volume = {abs/2308.06547},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2308.06547},
doi = {10.48550/ARXIV.2308.06547},
eprinttype = {arXiv},
eprint = {2308.06547},
timestamp = {Mon, 03 Jun 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2308-06547.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2309-07377,
author = {Yifan Yang and
Feiyu Shen and
Chenpeng Du and
Ziyang Ma and
Kai Yu and
Daniel Povey and
Xie Chen},
title = {Towards Universal Speech Discrete Tokens: {A} Case Study for {ASR}
and {TTS}},
journal = {CoRR},
volume = {abs/2309.07377},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2309.07377},
doi = {10.48550/ARXIV.2309.07377},
eprinttype = {arXiv},
eprint = {2309.07377},
timestamp = {Wed, 20 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2309-07377.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2309-07414,
author = {Xiaoyu Yang and
Wei Kang and
Zengwei Yao and
Yifan Yang and
Liyong Guo and
Fangjun Kuang and
Long Lin and
Daniel Povey},
title = {PromptASR for contextualized {ASR} with controllable style},
journal = {CoRR},
volume = {abs/2309.07414},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2309.07414},
doi = {10.48550/ARXIV.2309.07414},
eprinttype = {arXiv},
eprint = {2309.07414},
timestamp = {Thu, 21 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2309-07414.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2309-08105,
author = {Wei Kang and
Xiaoyu Yang and
Zengwei Yao and
Fangjun Kuang and
Yifan Yang and
Liyong Guo and
Long Lin and
Daniel Povey},
title = {Libriheavy: a 50, 000 hours {ASR} corpus with punctuation casing and
context},
journal = {CoRR},
volume = {abs/2309.08105},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2309.08105},
doi = {10.48550/ARXIV.2309.08105},
eprinttype = {arXiv},
eprint = {2309.08105},
timestamp = {Tue, 26 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2309-08105.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2309-15796,
author = {Dongji Gao and
Hainan Xu and
Desh Raj and
Leibny Paola Garc{\'{\i}}a{-}Perera and
Daniel Povey and
Sanjeev Khudanpur},
title = {Learning from Flawed Data: Weakly Supervised Automatic Speech Recognition},
journal = {CoRR},
volume = {abs/2309.15796},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2309.15796},
doi = {10.48550/ARXIV.2309.15796},
eprinttype = {arXiv},
eprint = {2309.15796},
timestamp = {Mon, 05 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2309-15796.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2310-11230,
author = {Zengwei Yao and
Liyong Guo and
Xiaoyu Yang and
Wei Kang and
Fangjun Kuang and
Yifan Yang and
Zengrui Jin and
Long Lin and
Daniel Povey},
title = {Zipformer: {A} faster and better encoder for automatic speech recognition},
journal = {CoRR},
volume = {abs/2310.11230},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2310.11230},
doi = {10.48550/ARXIV.2310.11230},
eprinttype = {arXiv},
eprint = {2310.11230},
timestamp = {Thu, 26 Oct 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2310-11230.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/KuangGKLLYP22,
author = {Fangjun Kuang and
Liyong Guo and
Wei Kang and
Long Lin and
Mingshuang Luo and
Zengwei Yao and
Daniel Povey},
editor = {Hanseok Ko and
John H. L. Hansen},
title = {Pruned {RNN-T} for fast, memory-efficient {ASR} training},
booktitle = {23rd Annual Conference of the International Speech Communication Association,
Interspeech 2022, Incheon, Korea, September 18-22, 2022},
pages = {2068--2072},
publisher = {{ISCA}},
year = {2022},
url = {https://doi.org/10.21437/Interspeech.2022-10340},
doi = {10.21437/INTERSPEECH.2022-10340},
timestamp = {Tue, 11 Jun 2024 16:45:43 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/KuangGKLLYP22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@proceedings{DBLP:conf/cicai/2022-1,
editor = {Lu Fang and
Daniel Povey and
Guangtao Zhai and
Tao Mei and
Ruiping Wang},
title = {Artificial Intelligence - Second {CAAI} International Conference,
{CICAI} 2022, Beijing, China, August 27-28, 2022, Revised Selected
Papers, Part {I}},
series = {Lecture Notes in Computer Science},
volume = {13604},
publisher = {Springer},
year = {2022},
url = {https://doi.org/10.1007/978-3-031-20497-5},
doi = {10.1007/978-3-031-20497-5},
isbn = {978-3-031-20496-8},
timestamp = {Mon, 12 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/cicai/2022-1.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@proceedings{DBLP:conf/cicai/2022-2,
editor = {Lu Fang and
Daniel Povey and
Guangtao Zhai and
Tao Mei and
Ruiping Wang},
title = {Artificial Intelligence - Second {CAAI} International Conference,
{CICAI} 2022, Beijing, China, August 27-28, 2022, Revised Selected
Papers, Part {II}},
series = {Lecture Notes in Computer Science},
volume = {13605},
publisher = {Springer},
year = {2022},
url = {https://doi.org/10.1007/978-3-031-20500-2},
doi = {10.1007/978-3-031-20500-2},
isbn = {978-3-031-20499-9},
timestamp = {Mon, 12 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/cicai/2022-2.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@proceedings{DBLP:conf/cicai/2022-3,
editor = {Lu Fang and
Daniel Povey and
Guangtao Zhai and
Tao Mei and
Ruiping Wang},
title = {Artificial Intelligence - Second {CAAI} International Conference,
{CICAI} 2022, Beijing, China, August 27-28, 2022, Revised Selected
Papers, Part {III}},
series = {Lecture Notes in Computer Science},
volume = {13606},
publisher = {Springer},
year = {2022},
url = {https://doi.org/10.1007/978-3-031-20503-3},
doi = {10.1007/978-3-031-20503-3},
isbn = {978-3-031-20502-6},
timestamp = {Mon, 12 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/cicai/2022-3.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2206-13236,
author = {Fangjun Kuang and
Liyong Guo and
Wei Kang and
Long Lin and
Mingshuang Luo and
Zengwei Yao and
Daniel Povey},
title = {Pruned {RNN-T} for fast, memory-efficient {ASR} training},
journal = {CoRR},
volume = {abs/2206.13236},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2206.13236},
doi = {10.48550/ARXIV.2206.13236},
eprinttype = {arXiv},
eprint = {2206.13236},
timestamp = {Fri, 19 May 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2206-13236.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2211-00484,
author = {Wei Kang and
Liyong Guo and
Fangjun Kuang and
Long Lin and
Mingshuang Luo and
Zengwei Yao and
Xiaoyu Yang and
Piotr Zelasko and
Daniel Povey},
title = {Fast and parallel decoding for transducer},
journal = {CoRR},
volume = {abs/2211.00484},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2211.00484},
doi = {10.48550/ARXIV.2211.00484},
eprinttype = {arXiv},
eprint = {2211.00484},
timestamp = {Fri, 19 May 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2211-00484.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2211-00490,
author = {Wei Kang and
Zengwei Yao and
Fangjun Kuang and
Liyong Guo and
Xiaoyu Yang and
Long Lin and
Piotr Zelasko and
Daniel Povey},
title = {Delay-penalized transducer for low-latency streaming {ASR}},
journal = {CoRR},
volume = {abs/2211.00490},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2211.00490},
doi = {10.48550/ARXIV.2211.00490},
eprinttype = {arXiv},
eprint = {2211.00490},
timestamp = {Fri, 19 May 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2211-00490.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2211-00508,
author = {Liyong Guo and
Xiaoyu Yang and
Quandong Wang and
Yuxiang Kong and
Zengwei Yao and
Fan Cui and
Fangjun Kuang and
Wei Kang and
Long Lin and
Mingshuang Luo and
Piotr Zelasko and
Daniel Povey},
title = {Predicting Multi-Codebook Vector Quantization Indexes for Knowledge
Distillation},
journal = {CoRR},
volume = {abs/2211.00508},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2211.00508},
doi = {10.48550/ARXIV.2211.00508},
eprinttype = {arXiv},
eprint = {2211.00508},
timestamp = {Fri, 19 May 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2211-00508.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2212-05271,
author = {Desh Raj and
Daniel Povey and
Sanjeev Khudanpur},
title = {GPU-accelerated Guided Source Separation for Meeting Transcription},
journal = {CoRR},
volume = {abs/2212.05271},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2212.05271},
doi = {10.48550/ARXIV.2212.05271},
eprinttype = {arXiv},
eprint = {2212.05271},
timestamp = {Mon, 05 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2212-05271.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/spl/LvPYLWXK21,
author = {Hang Lv and
Daniel Povey and
Mahsa Yarmohammadi and
Ke Li and
Yiming Wang and
Lei Xie and
Sanjeev Khudanpur},
title = {LET-Decoder: {A} WFST-Based Lazy-Evaluation Token-Group Decoder With
Exact Lattice Generation},
journal = {{IEEE} Signal Process. Lett.},
volume = {28},
pages = {703--707},
year = {2021},
url = {https://doi.org/10.1109/LSP.2021.3067220},
doi = {10.1109/LSP.2021.3067220},
timestamp = {Mon, 25 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/spl/LvPYLWXK21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/Wang0P0K21,
author = {Yiming Wang and
Hang Lv and
Daniel Povey and
Lei Xie and
Sanjeev Khudanpur},
title = {Wake Word Detection with Streaming Transformers},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2021, Toronto, ON, Canada, June 6-11, 2021},
pages = {5864--5868},
publisher = {{IEEE}},
year = {2021},
url = {https://doi.org/10.1109/ICASSP39728.2021.9414777},
doi = {10.1109/ICASSP39728.2021.9414777},
timestamp = {Mon, 25 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/Wang0P0K21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/0001CXP0K21,
author = {Hang Lv and
Zhehuai Chen and
Hainan Xu and
Daniel Povey and
Lei Xie and
Sanjeev Khudanpur},
title = {An Asynchronous WFST-Based Decoder for Automatic Speech Recognition},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2021, Toronto, ON, Canada, June 6-11, 2021},
pages = {6019--6023},
publisher = {{IEEE}},
year = {2021},
url = {https://doi.org/10.1109/ICASSP39728.2021.9414509},
doi = {10.1109/ICASSP39728.2021.9414509},
timestamp = {Fri, 09 Jul 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/0001CXP0K21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/LiPK21,
author = {Ke Li and
Daniel Povey and
Sanjeev Khudanpur},
title = {A Parallelizable Lattice Rescoring Strategy with Neural Language Models},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2021, Toronto, ON, Canada, June 6-11, 2021},
pages = {6518--6522},
publisher = {{IEEE}},
year = {2021},
url = {https://doi.org/10.1109/ICASSP39728.2021.9414714},
doi = {10.1109/ICASSP39728.2021.9414714},
timestamp = {Tue, 06 Dec 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/LiPK21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/HanPTMP21,
author = {Kyu Jeong Han and
Jing Pan and
Venkata Krishna Naveen Tadala and
Tao Ma and
Dan Povey},
title = {Multistream {CNN} for Robust Acoustic Modeling},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2021, Toronto, ON, Canada, June 6-11, 2021},
pages = {6873--6877},
publisher = {{IEEE}},
year = {2021},
url = {https://doi.org/10.1109/ICASSP39728.2021.9414639},
doi = {10.1109/ICASSP39728.2021.9414639},
timestamp = {Fri, 08 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/HanPTMP21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/ChenCWDZWSPTZJK21,
author = {Guoguo Chen and
Shuzhou Chai and
Guan{-}Bo Wang and
Jiayu Du and
Wei{-}Qiang Zhang and
Chao Weng and
Dan Su and
Daniel Povey and
Jan Trmal and
Junbo Zhang and
Mingjie Jin and
Sanjeev Khudanpur and
Shinji Watanabe and
Shuaijiang Zhao and
Wei Zou and
Xiangang Li and
Xuchen Yao and
Yongqing Wang and
Zhao You and
Zhiyong Yan},
editor = {Hynek Hermansky and
Honza Cernock{\'{y}} and
Luk{\'{a}}s Burget and
Lori Lamel and
Odette Scharenborg and
Petr Motl{\'{\i}}cek},
title = {GigaSpeech: An Evolving, Multi-Domain {ASR} Corpus with 10, 000 Hours
of Transcribed Audio},
booktitle = {22nd Annual Conference of the International Speech Communication Association,
Interspeech 2021, Brno, Czechia, August 30 - September 3, 2021},
pages = {3670--3674},
publisher = {{ISCA}},
year = {2021},
url = {https://doi.org/10.21437/Interspeech.2021-1965},
doi = {10.21437/INTERSPEECH.2021-1965},
timestamp = {Tue, 11 Jun 2024 16:45:43 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/ChenCWDZWSPTZJK21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/ZhangZWYSHLPW21,
author = {Junbo Zhang and
Zhiwen Zhang and
Yongqing Wang and
Zhiyong Yan and
Qiong Song and
Yukai Huang and
Ke Li and
Daniel Povey and
Yujun Wang},
editor = {Hynek Hermansky and
Honza Cernock{\'{y}} and
Luk{\'{a}}s Burget and
Lori Lamel and
Odette Scharenborg and
Petr Motl{\'{\i}}cek},
title = {speechocean762: An Open-Source Non-Native English Speech Corpus for
Pronunciation Assessment},
booktitle = {22nd Annual Conference of the International Speech Communication Association,
Interspeech 2021, Brno, Czechia, August 30 - September 3, 2021},
pages = {3710--3714},
publisher = {{ISCA}},
year = {2021},
url = {https://doi.org/10.21437/Interspeech.2021-1259},
doi = {10.21437/INTERSPEECH.2021-1259},
timestamp = {Wed, 21 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/ZhangZWYSHLPW21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/slt/RajGH0PSK21,
author = {Desh Raj and
Leibny Paola Garc{\'{\i}}a{-}Perera and
Zili Huang and
Shinji Watanabe and
Daniel Povey and
Andreas Stolcke and
Sanjeev Khudanpur},
title = {DOVER-Lap: {A} Method for Combining Overlap-Aware Diarization Outputs},
booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen,
China, January 19-22, 2021},
pages = {881--888},
publisher = {{IEEE}},
year = {2021},
url = {https://doi.org/10.1109/SLT48900.2021.9383490},
doi = {10.1109/SLT48900.2021.9383490},
timestamp = {Mon, 05 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/slt/RajGH0PSK21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2102-04488,
author = {Yiming Wang and
Hang Lv and
Daniel Povey and
Lei Xie and
Sanjeev Khudanpur},
title = {Wake Word Detection with Streaming Transformers},
journal = {CoRR},
volume = {abs/2102.04488},
year = {2021},
url = {https://arxiv.org/abs/2102.04488},
eprinttype = {arXiv},
eprint = {2102.04488},
timestamp = {Mon, 25 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2102-04488.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2103-05081,
author = {Ke Li and
Daniel Povey and
Sanjeev Khudanpur},
title = {A Parallelizable Lattice Rescoring Strategy with Neural Language Models},
journal = {CoRR},
volume = {abs/2103.05081},
year = {2021},
url = {https://arxiv.org/abs/2103.05081},
eprinttype = {arXiv},
eprint = {2103.05081},
timestamp = {Tue, 06 Dec 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2103-05081.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2103-09063,
author = {Hang Lv and
Zhehuai Chen and
Hainan Xu and
Daniel Povey and
Lei Xie and
Sanjeev Khudanpur},
title = {An Asynchronous WFST-Based Decoder For Automatic Speech Recognition},
journal = {CoRR},
volume = {abs/2103.09063},
year = {2021},
url = {https://arxiv.org/abs/2103.09063},
eprinttype = {arXiv},
eprint = {2103.09063},
timestamp = {Tue, 23 Mar 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2103-09063.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2104-01378,
author = {Junbo Zhang and
Zhiwen Zhang and
Yongqing Wang and
Zhiyong Yan and
Qiong Song and
Yukai Huang and
Ke Li and
Daniel Povey and
Yujun Wang},
title = {speechocean762: An Open-Source Non-native English Speech Corpus For
Pronunciation Assessment},
journal = {CoRR},
volume = {abs/2104.01378},
year = {2021},
url = {https://arxiv.org/abs/2104.01378},
eprinttype = {arXiv},
eprint = {2104.01378},
timestamp = {Tue, 06 Dec 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2104-01378.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2106-06909,
author = {Guoguo Chen and
Shuzhou Chai and
Guanbo Wang and
Jiayu Du and
Wei{-}Qiang Zhang and
Chao Weng and
Dan Su and
Daniel Povey and
Jan Trmal and
Junbo Zhang and
Mingjie Jin and
Sanjeev Khudanpur and
Shinji Watanabe and
Shuaijiang Zhao and
Wei Zou and
Xiangang Li and
Xuchen Yao and
Yongqing Wang and
Yujun Wang and
Zhao You and
Zhiyong Yan},
title = {GigaSpeech: An Evolving, Multi-domain {ASR} Corpus with 10, 000 Hours
of Transcribed Audio},
journal = {CoRR},
volume = {abs/2106.06909},
year = {2021},
url = {https://arxiv.org/abs/2106.06909},
eprinttype = {arXiv},
eprint = {2106.06909},
timestamp = {Tue, 19 Jul 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2106-06909.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2110-12561,
author = {Piotr Zelasko and
Daniel Povey and
Jan "Yenda" Trmal and
Sanjeev Khudanpur},
title = {Lhotse: a speech data representation library for the modern deep learning
ecosystem},
journal = {CoRR},
volume = {abs/2110.12561},
year = {2021},
url = {https://arxiv.org/abs/2110.12561},
eprinttype = {arXiv},
eprint = {2110.12561},
timestamp = {Thu, 28 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2110-12561.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/ZhangPK20,
author = {Xiaohui Zhang and
Daniel Povey and
Sanjeev Khudanpur},
title = {{OOV} Recovery with Efficient 2nd Pass Decoding and Open-vocabulary
Word-level {RNNLM} Rescoring for Hybrid {ASR}},
booktitle = {2020 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2020, Barcelona, Spain, May 4-8, 2020},
pages = {6334--6338},
publisher = {{IEEE}},
year = {2020},
url = {https://doi.org/10.1109/ICASSP40776.2020.9053872},
doi = {10.1109/ICASSP40776.2020.9053872},
timestamp = {Thu, 04 Apr 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/ZhangPK20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/HuangWFGSPK20,
author = {Zili Huang and
Shinji Watanabe and
Yusuke Fujita and
Paola Garc{\'{\i}}a and
Yiwen Shao and
Daniel Povey and
Sanjeev Khudanpur},
title = {Speaker Diarization with Region Proposal Network},
booktitle = {2020 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2020, Barcelona, Spain, May 4-8, 2020},
pages = {6514--6518},
publisher = {{IEEE}},
year = {2020},
url = {https://doi.org/10.1109/ICASSP40776.2020.9053760},
doi = {10.1109/ICASSP40776.2020.9053760},
timestamp = {Sat, 30 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/HuangWFGSPK20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/BraunLLKP20,
author = {Hugo Braun and
Justin Luitjens and
Ryan Leary and
Tim Kaldewey and
Daniel Povey},
title = {Gpu-Accelerated Viterbi Exact Lattice Decoder for Batched Online and
Offline Speech Recognition},
booktitle = {2020 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2020, Barcelona, Spain, May 4-8, 2020},
pages = {7874--7878},
publisher = {{IEEE}},
year = {2020},
url = {https://doi.org/10.1109/ICASSP40776.2020.9054099},
doi = {10.1109/ICASSP40776.2020.9054099},
timestamp = {Thu, 23 Jul 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/BraunLLKP20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/LiLHHPPK20,
author = {Ke Li and
Zhe Liu and
Tianxing He and
Hongzhao Huang and
Fuchun Peng and
Daniel Povey and
Sanjeev Khudanpur},
title = {An Empirical Study of Transformer-Based Neural Language Model Adaptation},
booktitle = {2020 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2020, Barcelona, Spain, May 4-8, 2020},
pages = {7934--7938},
publisher = {{IEEE}},
year = {2020},
url = {https://doi.org/10.1109/ICASSP40776.2020.9053399},
doi = {10.1109/ICASSP40776.2020.9053399},
timestamp = {Tue, 06 Dec 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/LiLHHPPK20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/ShaoWPK20,
author = {Yiwen Shao and
Yiming Wang and
Daniel Povey and
Sanjeev Khudanpur},
editor = {Helen Meng and
Bo Xu and
Thomas Fang Zheng},
title = {PyChain: {A} Fully Parallelized PyTorch Implementation of {LF-MMI}
for End-to-End {ASR}},
booktitle = {21st Annual Conference of the International Speech Communication Association,
Interspeech 2020, Virtual Event, Shanghai, China, October 25-29, 2020},
pages = {561--565},
publisher = {{ISCA}},
year = {2020},
url = {https://doi.org/10.21437/Interspeech.2020-3053},
doi = {10.21437/INTERSPEECH.2020-3053},
timestamp = {Tue, 11 Jun 2024 16:45:43 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/ShaoWPK20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/GhahramaniHPHK20,
author = {Pegah Ghahramani and
Hossein Hadian and
Daniel Povey and
Hynek Hermansky and
Sanjeev Khudanpur},
editor = {Helen Meng and
Bo Xu and
Thomas Fang Zheng},
title = {An Alternative to MFCCs for {ASR}},
booktitle = {21st Annual Conference of the International Speech Communication Association,
Interspeech 2020, Virtual Event, Shanghai, China, October 25-29, 2020},
pages = {1664--1667},
publisher = {{ISCA}},
year = {2020},
url = {https://doi.org/10.21437/Interspeech.2020-2690},
doi = {10.21437/INTERSPEECH.2020-2690},
timestamp = {Sun, 04 Aug 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/GhahramaniHPHK20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/LiPK20,
author = {Ke Li and
Daniel Povey and
Sanjeev Khudanpur},
editor = {Helen Meng and
Bo Xu and
Thomas Fang Zheng},
title = {Neural Language Modeling with Implicit Cache Pointers},
booktitle = {21st Annual Conference of the International Speech Communication Association,
Interspeech 2020, Virtual Event, Shanghai, China, October 25-29, 2020},
pages = {3625--3629},
publisher = {{ISCA}},
year = {2020},
url = {https://doi.org/10.21437/Interspeech.2020-3020},
doi = {10.21437/INTERSPEECH.2020-3020},
timestamp = {Tue, 06 Dec 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/interspeech/LiPK20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/Wang0P0K20,
author = {Yiming Wang and
Hang Lv and
Daniel Povey and
Lei Xie and
Sanjeev Khudanpur},
editor = {Helen Meng and
Bo Xu and
Thomas Fang Zheng},
title = {Wake Word Detection with Alignment-Free Lattice-Free {MMI}},
booktitle = {21st Annual Conference of the International Speech Communication Association,
Interspeech 2020, Virtual Event, Shanghai, China, October 25-29, 2020},
pages = {4258--4262},
publisher = {{ISCA}},
year = {2020},
url = {https://doi.org/10.21437/Interspeech.2020-1811},
doi = {10.21437/INTERSPEECH.2020-1811},
timestamp = {Mon, 25 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/Wang0P0K20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/MadikeriKTMBP20,
author = {Srikanth R. Madikeri and
Banriskhem K. Khonglah and
Sibo Tong and
Petr Motl{\'{\i}}cek and
Herv{\'{e}} Bourlard and
Daniel Povey},
editor = {Helen Meng and
Bo Xu and
Thomas Fang Zheng},
title = {Lattice-Free Maximum Mutual Information Training of Multilingual Speech
Recognition Systems},
booktitle = {21st Annual Conference of the International Speech Communication Association,
Interspeech 2020, Virtual Event, Shanghai, China, October 25-29, 2020},
pages = {4746--4750},
publisher = {{ISCA}},
year = {2020},
url = {https://doi.org/10.21437/Interspeech.2020-2919},
doi = {10.21437/INTERSPEECH.2020-2919},
timestamp = {Fri, 29 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/interspeech/MadikeriKTMBP20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/HuangLAPK20,
author = {Ruizhe Huang and
Ke Li and
Ashish Arora and
Daniel Povey and
Sanjeev Khudanpur},
editor = {Helen Meng and
Bo Xu and
Thomas Fang Zheng},
title = {Efficient {MDI} Adaptation for n-Gram Language Models},
booktitle = {21st Annual Conference of the International Speech Communication Association,
Interspeech 2020, Virtual Event, Shanghai, China, October 25-29, 2020},
pages = {4916--4920},
publisher = {{ISCA}},
year = {2020},
url = {https://doi.org/10.21437/Interspeech.2020-2909},
doi = {10.21437/INTERSPEECH.2020-2909},
timestamp = {Tue, 06 Dec 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/interspeech/HuangLAPK20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2002-06220,
author = {Zili Huang and
Shinji Watanabe and
Yusuke Fujita and
Paola Garc{\'{\i}}a and
Yiwen Shao and
Daniel Povey and
Sanjeev Khudanpur},
title = {Speaker Diarization with Region Proposal Network},
journal = {CoRR},
volume = {abs/2002.06220},
year = {2020},
url = {https://arxiv.org/abs/2002.06220},
eprinttype = {arXiv},
eprint = {2002.06220},
timestamp = {Thu, 07 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2002-06220.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2005-08347,
author = {Yiming Wang and
Hang Lv and
Daniel Povey and
Lei Xie and
Sanjeev Khudanpur},
title = {Wake Word Detection with Alignment-Free Lattice-Free {MMI}},
journal = {CoRR},
volume = {abs/2005.08347},
year = {2020},
url = {https://arxiv.org/abs/2005.08347},
eprinttype = {arXiv},
eprint = {2005.08347},
timestamp = {Mon, 25 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2005-08347.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2005-09824,
author = {Yiwen Shao and
Yiming Wang and
Daniel Povey and
Sanjeev Khudanpur},
title = {PyChain: {A} Fully Parallelized PyTorch Implementation of {LF-MMI}
for End-to-End {ASR}},
journal = {CoRR},
volume = {abs/2005.09824},
year = {2020},
url = {https://arxiv.org/abs/2005.09824},
eprinttype = {arXiv},
eprint = {2005.09824},
timestamp = {Mon, 25 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2005-09824.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2005-10470,
author = {Kyu Jeong Han and
Jing Pan and
Venkata Krishna Naveen Tadala and
Tao Ma and
Dan Povey},
title = {Multistream {CNN} for Robust Acoustic Modeling},
journal = {CoRR},
volume = {abs/2005.10470},
year = {2020},
url = {https://arxiv.org/abs/2005.10470},
eprinttype = {arXiv},
eprint = {2005.10470},
timestamp = {Fri, 08 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2005-10470.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2008-02385,
author = {Ruizhe Huang and
Ke Li and
Ashish Arora and
Daniel Povey and
Sanjeev Khudanpur},
title = {Efficient {MDI} Adaptation for n-gram Language Models},
journal = {CoRR},
volume = {abs/2008.02385},
year = {2020},
url = {https://arxiv.org/abs/2008.02385},
eprinttype = {arXiv},
eprint = {2008.02385},
timestamp = {Tue, 06 Dec 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2008-02385.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2011-01997,
author = {Desh Raj and
Leibny Paola Garc{\'{\i}}a{-}Perera and
Zili Huang and
Shinji Watanabe and
Daniel Povey and
Andreas Stolcke and
Sanjeev Khudanpur},
title = {DOVER-Lap: {A} Method for Combining Overlap-aware Diarization Outputs},
journal = {CoRR},
volume = {abs/2011.01997},
year = {2020},
url = {https://arxiv.org/abs/2011.01997},
eprinttype = {arXiv},
eprint = {2011.01997},
timestamp = {Wed, 29 Dec 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2011-01997.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2011-02090,
author = {Desh Raj and
Jes{\'{u}}s Villalba and
Daniel Povey and
Sanjeev Khudanpur},
title = {Frustratingly Easy Noise-aware Training of Acoustic Models},
journal = {CoRR},
volume = {abs/2011.02090},
year = {2020},
url = {https://arxiv.org/abs/2011.02090},
eprinttype = {arXiv},
eprint = {2011.02090},
timestamp = {Wed, 26 Oct 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2011-02090.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/asru/ChenYXLXPK19,
author = {Zhehuai Chen and
Mahsa Yarmohammadi and
Hainan Xu and
Hang Lv and
Lei Xie and
Daniel Povey and
Sanjeev Khudanpur},
title = {Incremental Lattice Determinization for {WFST} Decoders},
booktitle = {{IEEE} Automatic Speech Recognition and Understanding Workshop, {ASRU}
2019, Singapore, December 14-18, 2019},
pages = {1--7},
publisher = {{IEEE}},
year = {2019},
url = {https://doi.org/10.1109/ASRU46091.2019.9004006},
doi = {10.1109/ASRU46091.2019.9004006},
timestamp = {Mon, 24 Feb 2020 17:51:31 +0100},
biburl = {https://dblp.org/rec/conf/asru/ChenYXLXPK19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/asru/RajSPK19,
author = {Desh Raj and
David Snyder and
Daniel Povey and
Sanjeev Khudanpur},
title = {Probing the Information Encoded in X-Vectors},
booktitle = {{IEEE} Automatic Speech Recognition and Understanding Workshop, {ASRU}
2019, Singapore, December 14-18, 2019},
pages = {726--733},
publisher = {{IEEE}},
year = {2019},
url = {https://doi.org/10.1109/ASRU46091.2019.9003979},
doi = {10.1109/ASRU46091.2019.9003979},
timestamp = {Mon, 05 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/asru/RajSPK19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/SnyderGSMPK19,
author = {David Snyder and
Daniel Garcia{-}Romero and
Gregory Sell and
Alan McCree and
Daniel Povey and
Sanjeev Khudanpur},
title = {Speaker Recognition for Multi-speaker Conversations Using X-vectors},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2019, Brighton, United Kingdom, May 12-17, 2019},
pages = {5796--5800},
publisher = {{IEEE}},
year = {2019},
url = {https://doi.org/10.1109/ICASSP.2019.8683760},
doi = {10.1109/ICASSP.2019.8683760},
timestamp = {Wed, 16 Oct 2019 14:14:52 +0200},
biburl = {https://dblp.org/rec/conf/icassp/SnyderGSMPK19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icdar/ChangAGEPK19,
author = {Chun{-}Chieh Chang and
Ashish Arora and
Leibny Paola Garc{\'{\i}}a{-}Perera and
David Etter and
Daniel Povey and
Sanjeev Khudanpur},
title = {Optical Character Recognition with Chinese and Korean Character Decomposition},
booktitle = {Second International Workshop on Machine Learning, WML@ICDAR 2019,
Sydney, Australia, September 22-25, 2019},
pages = {134--139},
publisher = {{IEEE}},
year = {2019},
url = {https://doi.org/10.1109/ICDARW.2019.40094},
doi = {10.1109/ICDARW.2019.40094},
timestamp = {Wed, 13 Nov 2019 17:12:21 +0100},
biburl = {https://dblp.org/rec/conf/icdar/ChangAGEPK19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icdar/AroraGWMSKCRBPE19,
author = {Ashish Arora and
Paola Garc{\'{\i}}a and
Shinji Watanabe and
Vimal Manohar and
Yiwen Shao and
Sanjeev Khudanpur and
Chun{-}Chieh Chang and
Babak Rekabdar and
Bagher BabaAli and
Daniel Povey and
David Etter and
Desh Raj and
Hossein Hadian and
Jan Trmal},
title = {Using {ASR} Methods for {OCR}},
booktitle = {2019 International Conference on Document Analysis and Recognition,
{ICDAR} 2019, Sydney, Australia, September 20-25, 2019},
pages = {663--668},
publisher = {{IEEE}},
year = {2019},
url = {https://doi.org/10.1109/ICDAR.2019.00111},
doi = {10.1109/ICDAR.2019.00111},
timestamp = {Mon, 05 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icdar/AroraGWMSKCRBPE19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/WuGPK19,
author = {Fei Wu and
Leibny Paola Garc{\'{\i}}a{-}Perera and
Daniel Povey and
Sanjeev Khudanpur},
editor = {Gernot Kubin and
Zdravko Kacic},
title = {Advances in Automatic Speech Recognition for Child Speech Using Factored
Time Delay Neural Network},
booktitle = {20th Annual Conference of the International Speech Communication Association,
Interspeech 2019, Graz, Austria, September 15-19, 2019},
pages = {1--5},
publisher = {{ISCA}},
year = {2019},
url = {https://doi.org/10.21437/Interspeech.2019-2980},
doi = {10.21437/INTERSPEECH.2019-2980},
timestamp = {Tue, 11 Jun 2024 16:45:43 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/WuGPK19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/XieGPK19,
author = {Jiamin Xie and
Leibny Paola Garc{\'{\i}}a{-}Perera and
Daniel Povey and
Sanjeev Khudanpur},
editor = {Gernot Kubin and
Zdravko Kacic},
title = {Multi-PLDA Diarization on Children's Speech},
booktitle = {20th Annual Conference of the International Speech Communication Association,
Interspeech 2019, Graz, Austria, September 15-19, 2019},
pages = {376--380},
publisher = {{ISCA}},
year = {2019},
url = {https://doi.org/10.21437/Interspeech.2019-2961},
doi = {10.21437/INTERSPEECH.2019-2961},
timestamp = {Fri, 29 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/interspeech/XieGPK19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/VillalbaCSGMSBR19,
author = {Jes{\'{u}}s Villalba and
Nanxin Chen and
David Snyder and
Daniel Garcia{-}Romero and
Alan McCree and
Gregory Sell and
Jonas Borgstrom and
Fred Richardson and
Suwon Shon and
Fran{\c{c}}ois Grondin and
R{\'{e}}da Dehak and
Leibny Paola Garc{\'{\i}}a{-}Perera and
Daniel Povey and
Pedro A. Torres{-}Carrasquillo and
Sanjeev Khudanpur and
Najim Dehak},
editor = {Gernot Kubin and
Zdravko Kacic},
title = {State-of-the-Art Speaker Recognition for Telephone and Video Speech:
The {JHU-MIT} Submission for {NIST} {SRE18}},
booktitle = {20th Annual Conference of the International Speech Communication Association,
Interspeech 2019, Graz, Austria, September 15-19, 2019},
pages = {1488--1492},
publisher = {{ISCA}},
year = {2019},
url = {https://doi.org/10.21437/Interspeech.2019-2713},
doi = {10.21437/INTERSPEECH.2019-2713},
timestamp = {Wed, 26 Oct 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/VillalbaCSGMSBR19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/Garcia-RomeroSS19,
author = {Daniel Garcia{-}Romero and
David Snyder and
Gregory Sell and
Alan McCree and
Daniel Povey and
Sanjeev Khudanpur},
editor = {Gernot Kubin and
Zdravko Kacic},
title = {x-Vector {DNN} Refinement with Full-Length Recordings for Speaker
Recognition},
booktitle = {20th Annual Conference of the International Speech Communication Association,
Interspeech 2019, Graz, Austria, September 15-19, 2019},
pages = {1493--1496},
publisher = {{ISCA}},
year = {2019},
url = {https://doi.org/10.21437/Interspeech.2019-2205},
doi = {10.21437/INTERSPEECH.2019-2205},
timestamp = {Fri, 29 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/interspeech/Garcia-RomeroSS19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/Garcia-RomeroSW19,
author = {Daniel Garcia{-}Romero and
David Snyder and
Shinji Watanabe and
Gregory Sell and
Alan McCree and
Daniel Povey and
Sanjeev Khudanpur},
editor = {Gernot Kubin and
Zdravko Kacic},
title = {Speaker Recognition Benchmark Using the CHiME-5 Corpus},
booktitle = {20th Annual Conference of the International Speech Communication Association,
Interspeech 2019, Graz, Austria, September 15-19, 2019},
pages = {1506--1510},
publisher = {{ISCA}},
year = {2019},
url = {https://doi.org/10.21437/Interspeech.2019-2174},
doi = {10.21437/INTERSPEECH.2019-2174},
timestamp = {Fri, 29 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/interspeech/Garcia-RomeroSW19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/SnyderVCPSDK19,
author = {David Snyder and
Jes{\'{u}}s Villalba and
Nanxin Chen and
Daniel Povey and
Gregory Sell and
Najim Dehak and
Sanjeev Khudanpur},
editor = {Gernot Kubin and
Zdravko Kacic},
title = {The {JHU} Speaker Recognition System for the VOiCES 2019 Challenge},
booktitle = {20th Annual Conference of the International Speech Communication Association,
Interspeech 2019, Graz, Austria, September 15-19, 2019},
pages = {2468--2472},
publisher = {{ISCA}},
year = {2019},
url = {https://doi.org/10.21437/Interspeech.2019-2979},
doi = {10.21437/INTERSPEECH.2019-2979},
timestamp = {Wed, 26 Oct 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/SnyderVCPSDK19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/WangSXMNPK19,
author = {Yiming Wang and
David Snyder and
Hainan Xu and
Vimal Manohar and
Phani Sankar Nidadavolu and
Daniel Povey and
Sanjeev Khudanpur},
editor = {Gernot Kubin and
Zdravko Kacic},
title = {The {JHU} {ASR} System for VOiCES from a Distance Challenge 2019},
booktitle = {20th Annual Conference of the International Speech Communication Association,
Interspeech 2019, Graz, Austria, September 15-19, 2019},
pages = {2488--2492},
publisher = {{ISCA}},
year = {2019},
url = {https://doi.org/10.21437/Interspeech.2019-1948},
doi = {10.21437/INTERSPEECH.2019-1948},
timestamp = {Mon, 25 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/WangSXMNPK19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/SarmaGPGSD19,
author = {Mousmita Sarma and
Pegah Ghahremani and
Daniel Povey and
Nagendra Kumar Goel and
Kandarpa Kumar Sarma and
Najim Dehak},
editor = {Gernot Kubin and
Zdravko Kacic},
title = {Improving Emotion Identification Using Phone Posteriors in Raw Speech
Waveform Based {DNN}},
booktitle = {20th Annual Conference of the International Speech Communication Association,
Interspeech 2019, Graz, Austria, September 15-19, 2019},
pages = {3925--3929},
publisher = {{ISCA}},
year = {2019},
url = {https://doi.org/10.21437/Interspeech.2019-2093},
doi = {10.21437/INTERSPEECH.2019-2093},
timestamp = {Sat, 30 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/SarmaGPGSD19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/mtsummit/YarmohammadiMHR19,
author = {Mahsa Yarmohammadi and
Xutai Ma and
Sorami Hisamoto and
Muhammad Rahman and
Yiming Wang and
Hainan Xu and
Daniel Povey and
Philipp Koehn and
Kevin Duh},
editor = {Mikel L. Forcada and
Andy Way and
Barry Haddow and
Rico Sennrich},
title = {Robust Document Representations for Cross-Lingual Information Retrieval
in Low-Resource Settings},
booktitle = {Proceedings of Machine Translation Summit {XVII} Volume 1: Research
Track, MTSummit 2019, Dublin, Ireland, August 19-23, 2019},
pages = {12--20},
publisher = {European Association for Machine Translation},
year = {2019},
url = {https://aclanthology.org/W19-6602/},
timestamp = {Mon, 25 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/mtsummit/YarmohammadiMHR19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1909-06351,
author = {Desh Raj and
David Snyder and
Daniel Povey and
Sanjeev Khudanpur},
title = {Probing the Information Encoded in x-vectors},
journal = {CoRR},
volume = {abs/1909.06351},
year = {2019},
url = {http://arxiv.org/abs/1909.06351},
eprinttype = {arXiv},
eprint = {1909.06351},
timestamp = {Wed, 18 Sep 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1909-06351.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/spl/PeddintiWPK18,
author = {Vijayaditya Peddinti and
Yiming Wang and
Daniel Povey and
Sanjeev Khudanpur},
title = {Low Latency Acoustic Modeling Using Temporal Convolution and LSTMs},
journal = {{IEEE} Signal Process. Lett.},
volume = {25},
number = {3},
pages = {373--377},
year = {2018},
url = {https://doi.org/10.1109/LSP.2017.2723507},
doi = {10.1109/LSP.2017.2723507},
timestamp = {Mon, 25 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/spl/PeddintiWPK18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/taslp/HadianSPK18,
author = {Hossein Hadian and
Hossein Sameti and
Daniel Povey and
Sanjeev Khudanpur},
title = {Flat-Start Single-Stage Discriminatively Trained HMM-Based Models
for {ASR}},
journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.},
volume = {26},
number = {11},
pages = {1949--1961},
year = {2018},
url = {https://doi.org/10.1109/TASLP.2018.2848701},
doi = {10.1109/TASLP.2018.2848701},
timestamp = {Fri, 13 Mar 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/taslp/HadianSPK18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iberspeech/HuangGVPD18,
author = {Zili Huang and
L. Paola Garc{\'{\i}}a{-}Perera and
Jes{\'{u}}s Villalba and
Daniel Povey and
Najim Dehak},
editor = {Jordi Luque and
Antonio Bonafonte and
Francesc Al{\'{\i}}as Pujol and
Ant{\'{o}}nio J. S. Teixeira},
title = {{JHU} Diarization System Description},
booktitle = {Fourth International Conference, IberSPEECH 2018, Barcelona, Spain,
21-23 November 2018, Proceedings},
pages = {236--239},
publisher = {{ISCA}},
year = {2018},
url = {https://doi.org/10.21437/IberSPEECH.2018-49},
doi = {10.21437/IBERSPEECH.2018-49},
timestamp = {Tue, 21 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/iberspeech/HuangGVPD18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/ManoharHPK18,
author = {Vimal Manohar and
Hossein Hadian and
Daniel Povey and
Sanjeev Khudanpur},
title = {Semi-Supervised Training of Acoustic Models Using Lattice-Free {MMI}},
booktitle = {2018 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2018, Calgary, AB, Canada, April 15-20, 2018},
pages = {4844--4848},
publisher = {{IEEE}},
year = {2018},
url = {https://doi.org/10.1109/ICASSP.2018.8462331},
doi = {10.1109/ICASSP.2018.8462331},
timestamp = {Mon, 15 Jun 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/ManoharHPK18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/SnyderGSPK18,
author = {David Snyder and
Daniel Garcia{-}Romero and
Gregory Sell and
Daniel Povey and
Sanjeev Khudanpur},
title = {X-Vectors: Robust {DNN} Embeddings for Speaker Recognition},
booktitle = {2018 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2018, Calgary, AB, Canada, April 15-20, 2018},
pages = {5329--5333},
publisher = {{IEEE}},
year = {2018},
url = {https://doi.org/10.1109/ICASSP.2018.8461375},
doi = {10.1109/ICASSP.2018.8461375},
timestamp = {Tue, 18 Sep 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/SnyderGSPK18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/PoveyHGLK18,
author = {Daniel Povey and
Hossein Hadian and
Pegah Ghahremani and
Ke Li and
Sanjeev Khudanpur},
title = {A Time-Restricted Self-Attention Layer for {ASR}},
booktitle = {2018 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2018, Calgary, AB, Canada, April 15-20, 2018},
pages = {5874--5878},
publisher = {{IEEE}},
year = {2018},
url = {https://doi.org/10.1109/ICASSP.2018.8462497},
doi = {10.1109/ICASSP.2018.8462497},
timestamp = {Tue, 06 Dec 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/PoveyHGLK18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/XuCGWLGCPK18,
author = {Hainan Xu and
Tongfei Chen and
Dongji Gao and
Yiming Wang and
Ke Li and
Nagendra Goel and
Yishay Carmiel and
Daniel Povey and
Sanjeev Khudanpur},
title = {A Pruned Rnnlm Lattice-Rescoring Algorithm for Automatic Speech Recognition},
booktitle = {2018 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2018, Calgary, AB, Canada, April 15-20, 2018},
pages = {5929--5933},
publisher = {{IEEE}},
year = {2018},
url = {https://doi.org/10.1109/ICASSP.2018.8461974},
doi = {10.1109/ICASSP.2018.8461974},
timestamp = {Mon, 25 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/XuCGWLGCPK18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/XuLWWKCPK18,
author = {Hainan Xu and
Ke Li and
Yiming Wang and
Jian Wang and
Shiyin Kang and
Xie Chen and
Daniel Povey and
Sanjeev Khudanpur},
title = {Neural Network Language Modeling with Letter-Based Features and Importance
Sampling},
booktitle = {2018 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2018, Calgary, AB, Canada, April 15-20, 2018},
pages = {6109--6113},
publisher = {{IEEE}},
year = {2018},
url = {https://doi.org/10.1109/ICASSP.2018.8461704},
doi = {10.1109/ICASSP.2018.8461704},
timestamp = {Mon, 25 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/XuLWWKCPK18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/HadianSPK18,
author = {Hossein Hadian and
Hossein Sameti and
Daniel Povey and
Sanjeev Khudanpur},
editor = {B. Yegnanarayana},
title = {End-to-end Speech Recognition Using Lattice-free {MMI}},
booktitle = {19th Annual Conference of the International Speech Communication Association,
Interspeech 2018, Hyderabad, India, September 2-6, 2018},
pages = {12--16},
publisher = {{ISCA}},
year = {2018},
url = {https://doi.org/10.21437/Interspeech.2018-1423},
doi = {10.21437/INTERSPEECH.2018-1423},
timestamp = {Tue, 11 Jun 2024 16:45:43 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/HadianSPK18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/GhahremaniNCVPK18,
author = {Pegah Ghahremani and
Phani Sankar Nidadavolu and
Nanxin Chen and
Jes{\'{u}}s Villalba and
Daniel Povey and
Sanjeev Khudanpur and
Najim Dehak},
editor = {B. Yegnanarayana},
title = {End-to-end Deep Neural Network Age Estimation},
booktitle = {19th Annual Conference of the International Speech Communication Association,
Interspeech 2018, Hyderabad, India, September 2-6, 2018},
pages = {277--281},
publisher = {{ISCA}},
year = {2018},
url = {https://doi.org/10.21437/Interspeech.2018-2015},
doi = {10.21437/INTERSPEECH.2018-2015},
timestamp = {Wed, 26 Oct 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/GhahremaniNCVPK18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/GhahremaniHLPK18,
author = {Pegah Ghahremani and
Hossein Hadian and
Hang Lv and
Daniel Povey and
Sanjeev Khudanpur},
editor = {B. Yegnanarayana},
title = {Acoustic Modeling from Frequency Domain Representations of Speech},
booktitle = {19th Annual Conference of the International Speech Communication Association,
Interspeech 2018, Hyderabad, India, September 2-6, 2018},
pages = {1596--1600},
publisher = {{ISCA}},
year = {2018},
url = {https://doi.org/10.21437/Interspeech.2018-1453},
doi = {10.21437/INTERSPEECH.2018-1453},
timestamp = {Fri, 29 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/interspeech/GhahremaniHLPK18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/ChengPHXK018,
author = {Gaofeng Cheng and
Daniel Povey and
Lu Huang and
Ji Xu and
Sanjeev Khudanpur and
Yonghong Yan},
editor = {B. Yegnanarayana},
title = {Output-Gate Projected Gated Recurrent Unit for Speech Recognition},
booktitle = {19th Annual Conference of the International Speech Communication Association,
Interspeech 2018, Hyderabad, India, September 2-6, 2018},
pages = {1793--1797},
publisher = {{ISCA}},
year = {2018},
url = {https://doi.org/10.21437/Interspeech.2018-1403},
doi = {10.21437/INTERSPEECH.2018-1403},
timestamp = {Fri, 29 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/interspeech/ChengPHXK018.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/ChenLXWPK18,
author = {Zhehuai Chen and
Justin Luitjens and
Hainan Xu and
Yiming Wang and
Daniel Povey and
Sanjeev Khudanpur},
editor = {B. Yegnanarayana},
title = {A GPU-based {WFST} Decoder with Exact Lattice Generation},
booktitle = {19th Annual Conference of the International Speech Communication Association,
Interspeech 2018, Hyderabad, India, September 2-6, 2018},
pages = {2212--2216},
publisher = {{ISCA}},
year = {2018},
url = {https://doi.org/10.21437/Interspeech.2018-1339},
doi = {10.21437/INTERSPEECH.2018-1339},
timestamp = {Mon, 25 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/ChenLXWPK18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/SellSMGVMMDPWK18,
author = {Gregory Sell and
David Snyder and
Alan McCree and
Daniel Garcia{-}Romero and
Jes{\'{u}}s Villalba and
Matthew Maciejewski and
Vimal Manohar and
Najim Dehak and
Daniel Povey and
Shinji Watanabe and
Sanjeev Khudanpur},
editor = {B. Yegnanarayana},
title = {Diarization is Hard: Some Experiences and Lessons Learned for the
{JHU} Team in the Inaugural {DIHARD} Challenge},
booktitle = {19th Annual Conference of the International Speech Communication Association,
Interspeech 2018, Hyderabad, India, September 2-6, 2018},
pages = {2808--2812},
publisher = {{ISCA}},
year = {2018},
url = {https://doi.org/10.21437/Interspeech.2018-1893},
doi = {10.21437/INTERSPEECH.2018-1893},
timestamp = {Mon, 26 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/SellSMGVMMDPWK18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/SarmaGPGSD18,
author = {Mousmita Sarma and
Pegah Ghahremani and
Daniel Povey and
Nagendra Kumar Goel and
Kandarpa Kumar Sarma and
Najim Dehak},
editor = {B. Yegnanarayana},
title = {Emotion Identification from Raw Speech Signals Using DNNs},
booktitle = {19th Annual Conference of the International Speech Communication Association,
Interspeech 2018, Hyderabad, India, September 2-6, 2018},
pages = {3097--3101},
publisher = {{ISCA}},
year = {2018},
url = {https://doi.org/10.21437/Interspeech.2018-1353},
doi = {10.21437/INTERSPEECH.2018-1353},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/SarmaGPGSD18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/LiXWPK18,
author = {Ke Li and
Hainan Xu and
Yiming Wang and
Daniel Povey and
Sanjeev Khudanpur},
editor = {B. Yegnanarayana},
title = {Recurrent Neural Network Language Model Adaptation for Conversational
Speech Recognition},
booktitle = {19th Annual Conference of the International Speech Communication Association,
Interspeech 2018, Hyderabad, India, September 2-6, 2018},
pages = {3373--3377},
publisher = {{ISCA}},
year = {2018},
url = {https://doi.org/10.21437/Interspeech.2018-1413},
doi = {10.21437/INTERSPEECH.2018-1413},
timestamp = {Mon, 25 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/LiXWPK18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/ZhuKSMP18,
author = {Yingke Zhu and
Tom Ko and
David Snyder and
Brian Mak and
Daniel Povey},
editor = {B. Yegnanarayana},
title = {Self-Attentive Speaker Embeddings for Text-Independent Speaker Verification},
booktitle = {19th Annual Conference of the International Speech Communication Association,
Interspeech 2018, Hyderabad, India, September 2-6, 2018},
pages = {3573--3577},
publisher = {{ISCA}},
year = {2018},
url = {https://doi.org/10.21437/Interspeech.2018-1158},
doi = {10.21437/INTERSPEECH.2018-1158},
timestamp = {Mon, 05 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/interspeech/ZhuKSMP18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/PoveyCWLXYK18,
author = {Daniel Povey and
Gaofeng Cheng and
Yiming Wang and
Ke Li and
Hainan Xu and
Mahsa Yarmohammadi and
Sanjeev Khudanpur},
editor = {B. Yegnanarayana},
title = {Semi-Orthogonal Low-Rank Matrix Factorization for Deep Neural Networks},
booktitle = {19th Annual Conference of the International Speech Communication Association,
Interspeech 2018, Hyderabad, India, September 2-6, 2018},
pages = {3743--3747},
publisher = {{ISCA}},
year = {2018},
url = {https://doi.org/10.21437/Interspeech.2018-1417},
doi = {10.21437/INTERSPEECH.2018-1417},
timestamp = {Sun, 12 Nov 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/interspeech/PoveyCWLXYK18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/odyssey/SnyderGMSPK18,
author = {David Snyder and
Daniel Garcia{-}Romero and
Alan McCree and
Gregory Sell and
Daniel Povey and
Sanjeev Khudanpur},
editor = {Anthony Larcher and
Jean{-}Fran{\c{c}}ois Bonastre},
title = {Spoken Language Recognition using X-vectors},
booktitle = {Odyssey 2018: The Speaker and Language Recognition Workshop, 26-29
June 2018, Les Sables d'Olonne, France},
pages = {105--111},
publisher = {{ISCA}},
year = {2018},
url = {https://doi.org/10.21437/Odyssey.2018-15},
doi = {10.21437/ODYSSEY.2018-15},
timestamp = {Tue, 30 Jul 2024 09:37:28 +0200},
biburl = {https://dblp.org/rec/conf/odyssey/SnyderGMSPK18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/slt/HadianPSTK18,
author = {Hossein Hadian and
Daniel Povey and
Hossein Sameti and
Jan Trmal and
Sanjeev Khudanpur},
title = {Improving {LF-MMI} Using Unconstrained Supervisions for {ASR}},
booktitle = {2018 {IEEE} Spoken Language Technology Workshop, {SLT} 2018, Athens,
Greece, December 18-21, 2018},
pages = {43--47},
publisher = {{IEEE}},
year = {2018},
url = {https://doi.org/10.1109/SLT.2018.8639684},
doi = {10.1109/SLT.2018.8639684},
timestamp = {Mon, 15 Jun 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/slt/HadianPSTK18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/slt/ManoharGPK18,
author = {Vimal Manohar and
Pegah Ghahremani and
Daniel Povey and
Sanjeev Khudanpur},
title = {A Teacher-Student Learning Approach for Unsupervised Domain Adaptation
of Sequence-Trained {ASR} Models},
booktitle = {2018 {IEEE} Spoken Language Technology Workshop, {SLT} 2018, Athens,
Greece, December 18-21, 2018},
pages = {250--257},
publisher = {{IEEE}},
year = {2018},
url = {https://doi.org/10.1109/SLT.2018.8639635},
doi = {10.1109/SLT.2018.8639635},
timestamp = {Fri, 15 Feb 2019 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/slt/ManoharGPK18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1804-03243,
author = {Zhehuai Chen and
Justin Luitjens and
Hainan Xu and
Yiming Wang and
Daniel Povey and
Sanjeev Khudanpur},
title = {A GPU-based {WFST} Decoder with Exact Lattice Generation},
journal = {CoRR},
volume = {abs/1804.03243},
year = {2018},
url = {http://arxiv.org/abs/1804.03243},
eprinttype = {arXiv},
eprint = {1804.03243},
timestamp = {Mon, 25 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1804-03243.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/asru/GhahremaniMHPK17,
author = {Pegah Ghahremani and
Vimal Manohar and
Hossein Hadian and
Daniel Povey and
Sanjeev Khudanpur},
title = {Investigation of transfer learning for {ASR} using {LF-MMI} trained
neural networks},
booktitle = {2017 {IEEE} Automatic Speech Recognition and Understanding Workshop,
{ASRU} 2017, Okinawa, Japan, December 16-20, 2017},
pages = {279--286},
publisher = {{IEEE}},
year = {2017},
url = {https://doi.org/10.1109/ASRU.2017.8268947},
doi = {10.1109/ASRU.2017.8268947},
timestamp = {Mon, 15 Jun 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/asru/GhahremaniMHPK17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/asru/ManoharPK17,
author = {Vimal Manohar and
Daniel Povey and
Sanjeev Khudanpur},
title = {{JHU} Kaldi system for Arabic {MGB-3} {ASR} challenge using diarization,
audio-transcript alignment and transfer learning},
booktitle = {2017 {IEEE} Automatic Speech Recognition and Understanding Workshop,
{ASRU} 2017, Okinawa, Japan, December 16-20, 2017},
pages = {346--352},
publisher = {{IEEE}},
year = {2017},
url = {https://doi.org/10.1109/ASRU.2017.8268956},
doi = {10.1109/ASRU.2017.8268956},
timestamp = {Tue, 30 Jan 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/asru/ManoharPK17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/Garcia-RomeroSS17,
author = {Daniel Garcia{-}Romero and
David Snyder and
Gregory Sell and
Daniel Povey and
Alan McCree},
title = {Speaker diarization using deep neural network embeddings},
booktitle = {2017 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2017, New Orleans, LA, USA, March 5-9, 2017},
pages = {4930--4934},
publisher = {{IEEE}},
year = {2017},
url = {https://doi.org/10.1109/ICASSP.2017.7953094},
doi = {10.1109/ICASSP.2017.7953094},
timestamp = {Wed, 16 Oct 2019 14:14:52 +0200},
biburl = {https://dblp.org/rec/conf/icassp/Garcia-RomeroSS17.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 = {Fri, 02 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/KoPPSK17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/HadianPSK17,
author = {Hossein Hadian and
Daniel Povey and
Hossein Sameti and
Sanjeev Khudanpur},
editor = {Francisco Lacerda},
title = {Phone Duration Modeling for {LVCSR} Using Neural Networks},
booktitle = {18th Annual Conference of the International Speech Communication Association,
Interspeech 2017, Stockholm, Sweden, August 20-24, 2017},
pages = {518--522},
publisher = {{ISCA}},
year = {2017},
url = {https://doi.org/10.21437/Interspeech.2017-1680},
doi = {10.21437/INTERSPEECH.2017-1680},
timestamp = {Tue, 11 Jun 2024 16:45:43 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/HadianPSK17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/SnyderGPK17,
author = {David Snyder and
Daniel Garcia{-}Romero and
Daniel Povey and
Sanjeev Khudanpur},
editor = {Francisco Lacerda},
title = {Deep Neural Network Embeddings for Text-Independent Speaker Verification},
booktitle = {18th Annual Conference of the International Speech Communication Association,
Interspeech 2017, Stockholm, Sweden, August 20-24, 2017},
pages = {999--1003},
publisher = {{ISCA}},
year = {2017},
url = {https://doi.org/10.21437/Interspeech.2017-620},
doi = {10.21437/INTERSPEECH.2017-620},
timestamp = {Sun, 12 Nov 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/interspeech/SnyderGPK17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/ChengPPMKY17,
author = {Gaofeng Cheng and
Vijayaditya Peddinti and
Daniel Povey and
Vimal Manohar and
Sanjeev Khudanpur and
Yonghong Yan},
editor = {Francisco Lacerda},
title = {An Exploration of Dropout with LSTMs},
booktitle = {18th Annual Conference of the International Speech Communication Association,
Interspeech 2017, Stockholm, Sweden, August 20-24, 2017},
pages = {1586--1590},
publisher = {{ISCA}},
year = {2017},
url = {https://doi.org/10.21437/Interspeech.2017-129},
doi = {10.21437/INTERSPEECH.2017-129},
timestamp = {Mon, 26 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/ChengPPMKY17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/WangPXZPK17,
author = {Yiming Wang and
Vijayaditya Peddinti and
Hainan Xu and
Xiaohui Zhang and
Daniel Povey and
Sanjeev Khudanpur},
editor = {Francisco Lacerda},
title = {Backstitch: Counteracting Finite-Sample Bias via Negative Steps},
booktitle = {18th Annual Conference of the International Speech Communication Association,
Interspeech 2017, Stockholm, Sweden, August 20-24, 2017},
pages = {1631--1635},
publisher = {{ISCA}},
year = {2017},
url = {https://doi.org/10.21437/Interspeech.2017-1323},
doi = {10.21437/INTERSPEECH.2017-1323},
timestamp = {Thu, 04 Apr 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/WangPXZPK17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/ZhangMPK17,
author = {Xiaohui Zhang and
Vimal Manohar and
Daniel Povey and
Sanjeev Khudanpur},
editor = {Francisco Lacerda},
title = {Acoustic Data-Driven Lexicon Learning Based on a Greedy Pronunciation
Selection Framework},
booktitle = {18th Annual Conference of the International Speech Communication Association,
Interspeech 2017, Stockholm, Sweden, August 20-24, 2017},
pages = {2541--2545},
publisher = {{ISCA}},
year = {2017},
url = {https://doi.org/10.21437/Interspeech.2017-588},
doi = {10.21437/INTERSPEECH.2017-588},
timestamp = {Thu, 04 Apr 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/ZhangMPK17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/TrmalWPZGWMXPK17,
author = {Jan Trmal and
Matthew Wiesner and
Vijayaditya Peddinti and
Xiaohui Zhang and
Pegah Ghahremani and
Yiming Wang and
Vimal Manohar and
Hainan Xu and
Daniel Povey and
Sanjeev Khudanpur},
editor = {Francisco Lacerda},
title = {The Kaldi OpenKWS System: Improving Low Resource Keyword Search},
booktitle = {18th Annual Conference of the International Speech Communication Association,
Interspeech 2017, Stockholm, Sweden, August 20-24, 2017},
pages = {3597--3601},
publisher = {{ISCA}},
year = {2017},
url = {https://doi.org/10.21437/Interspeech.2017-601},
doi = {10.21437/INTERSPEECH.2017-601},
timestamp = {Thu, 04 Apr 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/TrmalWPZGWMXPK17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/ZhangMPK17,
author = {Xiaohui Zhang and
Vimal Manohar and
Daniel Povey and
Sanjeev Khudanpur},
title = {Acoustic data-driven lexicon learning based on a greedy pronunciation
selection framework},
journal = {CoRR},
volume = {abs/1706.03747},
year = {2017},
url = {http://arxiv.org/abs/1706.03747},
eprinttype = {arXiv},
eprint = {1706.03747},
timestamp = {Thu, 04 Apr 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/ZhangMPK17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/ChenPK16,
author = {Guoguo Chen and
Daniel Povey and
Sanjeev Khudanpur},
title = {Acoustic data-driven pronunciation lexicon generation for logographic
languages},
booktitle = {2016 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2016, Shanghai, China, March 20-25, 2016},
pages = {5350--5354},
publisher = {{IEEE}},
year = {2016},
url = {https://doi.org/10.1109/ICASSP.2016.7472699},
doi = {10.1109/ICASSP.2016.7472699},
timestamp = {Wed, 16 Oct 2019 14:14:52 +0200},
biburl = {https://dblp.org/rec/conf/icassp/ChenPK16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/PeddintiMWPK16,
author = {Vijayaditya Peddinti and
Vimal Manohar and
Yiming Wang and
Daniel Povey and
Sanjeev Khudanpur},
editor = {Nelson Morgan},
title = {Far-Field {ASR} Without Parallel Data},
booktitle = {17th Annual Conference of the International Speech Communication Association,
Interspeech 2016, San Francisco, CA, USA, September 8-12, 2016},
pages = {1996--2000},
publisher = {{ISCA}},
year = {2016},
url = {https://doi.org/10.21437/Interspeech.2016-1475},
doi = {10.21437/INTERSPEECH.2016-1475},
timestamp = {Tue, 11 Jun 2024 16:45:43 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/PeddintiMWPK16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/PoveyPGGMNWK16,
author = {Daniel Povey and
Vijayaditya Peddinti and
Daniel Galvez and
Pegah Ghahremani and
Vimal Manohar and
Xingyu Na and
Yiming Wang and
Sanjeev Khudanpur},
editor = {Nelson Morgan},
title = {Purely Sequence-Trained Neural Networks for {ASR} Based on Lattice-Free
{MMI}},
booktitle = {17th Annual Conference of the International Speech Communication Association,
Interspeech 2016, San Francisco, CA, USA, September 8-12, 2016},
pages = {2751--2755},
publisher = {{ISCA}},
year = {2016},
url = {https://doi.org/10.21437/Interspeech.2016-595},
doi = {10.21437/INTERSPEECH.2016-595},
timestamp = {Sun, 12 Nov 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/interspeech/PoveyPGGMNWK16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/GhahremaniMPK16,
author = {Pegah Ghahremani and
Vimal Manohar and
Daniel Povey and
Sanjeev Khudanpur},
editor = {Nelson Morgan},
title = {Acoustic Modelling from the Signal Domain Using CNNs},
booktitle = {17th Annual Conference of the International Speech Communication Association,
Interspeech 2016, San Francisco, CA, USA, September 8-12, 2016},
pages = {3434--3438},
publisher = {{ISCA}},
year = {2016},
url = {https://doi.org/10.21437/Interspeech.2016-1495},
doi = {10.21437/INTERSPEECH.2016-1495},
timestamp = {Fri, 29 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/interspeech/GhahremaniMPK16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/slt/SnyderGPGCK16,
author = {David Snyder and
Pegah Ghahremani and
Daniel Povey and
Daniel Garcia{-}Romero and
Yishay Carmiel and
Sanjeev Khudanpur},
title = {Deep neural network-based speaker embeddings for end-to-end speaker
verification},
booktitle = {2016 {IEEE} Spoken Language Technology Workshop, {SLT} 2016, San Diego,
CA, USA, December 13-16, 2016},
pages = {165--170},
publisher = {{IEEE}},
year = {2016},
url = {https://doi.org/10.1109/SLT.2016.7846260},
doi = {10.1109/SLT.2016.7846260},
timestamp = {Wed, 16 Oct 2019 14:14:53 +0200},
biburl = {https://dblp.org/rec/conf/slt/SnyderGPGCK16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/asru/SnyderGP15,
author = {David Snyder and
Daniel Garcia{-}Romero and
Daniel Povey},
title = {Time delay deep neural network-based universal background models for
speaker recognition},
booktitle = {2015 {IEEE} Workshop on Automatic Speech Recognition and Understanding,
{ASRU} 2015, Scottsdale, AZ, USA, December 13-17, 2015},
pages = {92--97},
publisher = {{IEEE}},
year = {2015},
url = {https://doi.org/10.1109/ASRU.2015.7404779},
doi = {10.1109/ASRU.2015.7404779},
timestamp = {Wed, 16 Oct 2019 14:14:51 +0200},
biburl = {https://dblp.org/rec/conf/asru/SnyderGP15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/asru/PeddintiCMKPK15,
author = {Vijayaditya Peddinti and
Guoguo Chen and
Vimal Manohar and
Tom Ko and
Daniel Povey and
Sanjeev Khudanpur},
title = {{JHU} ASpIRE system: Robust {LVCSR} with TDNNS, iVector adaptation
and {RNN-LMS}},
booktitle = {2015 {IEEE} Workshop on Automatic Speech Recognition and Understanding,
{ASRU} 2015, Scottsdale, AZ, USA, December 13-17, 2015},
pages = {539--546},
publisher = {{IEEE}},
year = {2015},
url = {https://doi.org/10.1109/ASRU.2015.7404842},
doi = {10.1109/ASRU.2015.7404842},
timestamp = {Fri, 02 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/asru/PeddintiCMKPK15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/emnlp/KumarBTPK15,
author = {Gaurav Kumar and
Graeme W. Blackwood and
Jan Trmal and
Daniel Povey and
Sanjeev Khudanpur},
editor = {Llu{\'{\i}}s M{\`{a}}rquez and
Chris Callison{-}Burch and
Jian Su and
Daniele Pighin and
Yuval Marton},
title = {A Coarse-Grained Model for Optimal Coupling of {ASR} and {SMT} Systems
for Speech Translation},
booktitle = {Proceedings of the 2015 Conference on Empirical Methods in Natural
Language Processing, {EMNLP} 2015, Lisbon, Portugal, September 17-21,
2015},
pages = {1902--1907},
publisher = {The Association for Computational Linguistics},
year = {2015},
url = {https://doi.org/10.18653/v1/d15-1218},
doi = {10.18653/V1/D15-1218},
timestamp = {Fri, 06 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/emnlp/KumarBTPK15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/PanayotovCPK15,
author = {Vassil Panayotov and
Guoguo Chen and
Daniel Povey and
Sanjeev Khudanpur},
title = {Librispeech: An {ASR} corpus based on public domain audio books},
booktitle = {2015 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2015, South Brisbane, Queensland, Australia,
April 19-24, 2015},
pages = {5206--5210},
publisher = {{IEEE}},
year = {2015},
url = {https://doi.org/10.1109/ICASSP.2015.7178964},
doi = {10.1109/ICASSP.2015.7178964},
timestamp = {Fri, 25 Dec 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/PanayotovCPK15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/ChenXWPK15,
author = {Guoguo Chen and
Hainan Xu and
Minhua Wu and
Daniel Povey and
Sanjeev Khudanpur},
title = {Pronunciation and silence probability modeling for {ASR}},
booktitle = {16th Annual Conference of the International Speech Communication Association,
{INTERSPEECH} 2015, Dresden, Germany, September 6-10, 2015},
pages = {533--537},
publisher = {{ISCA}},
year = {2015},
url = {https://doi.org/10.21437/Interspeech.2015-198},
doi = {10.21437/INTERSPEECH.2015-198},
timestamp = {Tue, 11 Jun 2024 16:45:43 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/ChenXWPK15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/XuCPK15,
author = {Hainan Xu and
Guoguo Chen and
Daniel Povey and
Sanjeev Khudanpur},
title = {Modeling phonetic context with non-random forests for speech recognition},
booktitle = {16th Annual Conference of the International Speech Communication Association,
{INTERSPEECH} 2015, Dresden, Germany, September 6-10, 2015},
pages = {2117--2121},
publisher = {{ISCA}},
year = {2015},
url = {https://doi.org/10.21437/Interspeech.2015-478},
doi = {10.21437/INTERSPEECH.2015-478},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/XuCPK15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/PeddintiCPK15,
author = {Vijayaditya Peddinti and
Guoguo Chen and
Daniel Povey and
Sanjeev Khudanpur},
title = {Reverberation robust acoustic modeling using i-vectors with time delay
neural networks},
booktitle = {16th Annual Conference of the International Speech Communication Association,
{INTERSPEECH} 2015, Dresden, Germany, September 6-10, 2015},
pages = {2440--2444},
publisher = {{ISCA}},
year = {2015},
url = {https://doi.org/10.21437/Interspeech.2015-527},
doi = {10.21437/INTERSPEECH.2015-527},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/PeddintiCPK15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/ManoharPK15,
author = {Vimal Manohar and
Daniel Povey and
Sanjeev Khudanpur},
title = {Semi-supervised maximum mutual information training of deep neural
network acoustic models},
booktitle = {16th Annual Conference of the International Speech Communication Association,
{INTERSPEECH} 2015, Dresden, Germany, September 6-10, 2015},
pages = {2630--2634},
publisher = {{ISCA}},
year = {2015},
url = {https://doi.org/10.21437/Interspeech.2015-561},
doi = {10.21437/INTERSPEECH.2015-561},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/ManoharPK15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/PeddintiPK15,
author = {Vijayaditya Peddinti and
Daniel Povey and
Sanjeev Khudanpur},
title = {A time delay neural network architecture for efficient modeling of
long temporal contexts},
booktitle = {16th Annual Conference of the International Speech Communication Association,
{INTERSPEECH} 2015, Dresden, Germany, September 6-10, 2015},
pages = {3214--3218},
publisher = {{ISCA}},
year = {2015},
url = {https://doi.org/10.21437/Interspeech.2015-647},
doi = {10.21437/INTERSPEECH.2015-647},
timestamp = {Sun, 12 Nov 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/interspeech/PeddintiPK15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/KoPPK15,
author = {Tom Ko and
Vijayaditya Peddinti and
Daniel Povey and
Sanjeev Khudanpur},
title = {Audio augmentation for speech recognition},
booktitle = {16th Annual Conference of the International Speech Communication Association,
{INTERSPEECH} 2015, Dresden, Germany, September 6-10, 2015},
pages = {3586--3589},
publisher = {{ISCA}},
year = {2015},
url = {https://doi.org/10.21437/Interspeech.2015-711},
doi = {10.21437/INTERSPEECH.2015-711},
timestamp = {Sun, 12 Nov 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/interspeech/KoPPK15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/ZhangPK15,
author = {Xiaohui Zhang and
Daniel Povey and
Sanjeev Khudanpur},
title = {A diversity-penalizing ensemble training method for deep learning},
booktitle = {16th Annual Conference of the International Speech Communication Association,
{INTERSPEECH} 2015, Dresden, Germany, September 6-10, 2015},
pages = {3590--3594},
publisher = {{ISCA}},
year = {2015},
url = {https://doi.org/10.21437/Interspeech.2015-712},
doi = {10.21437/INTERSPEECH.2015-712},
timestamp = {Thu, 04 Apr 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/ZhangPK15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:journals/corr/PoveyZK14,
author = {Daniel Povey and
Xiaohui Zhang and
Sanjeev Khudanpur},
editor = {Yoshua Bengio and
Yann LeCun},
title = {Parallel training of Deep Neural Networks with Natural Gradient and
Parameter Averaging},
booktitle = {3rd International Conference on Learning Representations, {ICLR} 2015,
San Diego, CA, USA, May 7-9, 2015, Workshop Track Proceedings},
year = {2015},
url = {http://arxiv.org/abs/1410.7455},
timestamp = {Thu, 04 Apr 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/PoveyZK14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/SnyderCP15,
author = {David Snyder and
Guoguo Chen and
Daniel Povey},
title = {{MUSAN:} {A} Music, Speech, and Noise Corpus},
journal = {CoRR},
volume = {abs/1510.08484},
year = {2015},
url = {http://arxiv.org/abs/1510.08484},
eprinttype = {arXiv},
eprint = {1510.08484},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/SnyderCP15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/ZhangTPK14,
author = {Xiaohui Zhang and
Jan Trmal and
Daniel Povey and
Sanjeev Khudanpur},
title = {Improving deep neural network acoustic models using generalized maxout
networks},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2014, Florence, Italy, May 4-9, 2014},
pages = {215--219},
publisher = {{IEEE}},
year = {2014},
url = {https://doi.org/10.1109/ICASSP.2014.6853589},
doi = {10.1109/ICASSP.2014.6853589},
timestamp = {Thu, 04 Apr 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/ZhangTPK14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/GhahremaniBPRTK14,
author = {Pegah Ghahremani and
Bagher BabaAli and
Daniel Povey and
Korbinian Riedhammer and
Jan Trmal and
Sanjeev Khudanpur},
title = {A pitch extraction algorithm tuned for automatic speech recognition},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2014, Florence, Italy, May 4-9, 2014},
pages = {2494--2498},
publisher = {{IEEE}},
year = {2014},
url = {https://doi.org/10.1109/ICASSP.2014.6854049},
doi = {10.1109/ICASSP.2014.6854049},
timestamp = {Mon, 05 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/GhahremaniBPRTK14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/KumarPPK14,
author = {Gaurav Kumar and
Matt Post and
Daniel Povey and
Sanjeev Khudanpur},
title = {Some insights from translating conversational telephone speech},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2014, Florence, Italy, May 4-9, 2014},
pages = {3231--3235},
publisher = {{IEEE}},
year = {2014},
url = {https://doi.org/10.1109/ICASSP.2014.6854197},
doi = {10.1109/ICASSP.2014.6854197},
timestamp = {Fri, 19 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/KumarPPK14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/VuIPMSB14,
author = {Ngoc Thang Vu and
David Imseng and
Daniel Povey and
Petr Motl{\'{\i}}cek and
Tanja Schultz and
Herv{\'{e}} Bourlard},
title = {Multilingual deep neural network based acoustic modeling for rapid
language adaptation},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2014, Florence, Italy, May 4-9, 2014},
pages = {7639--7643},
publisher = {{IEEE}},
year = {2014},
url = {https://doi.org/10.1109/ICASSP.2014.6855086},
doi = {10.1109/ICASSP.2014.6855086},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/VuIPMSB14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/NoldenSPGMN14,
author = {David Nolden and
Hagen Soltau and
Daniel Povey and
Pegah Ghahremani and
Lidia Mangu and
Hermann Ney},
editor = {Haizhou Li and
Helen M. Meng and
Bin Ma and
Engsiong Chng and
Lei Xie},
title = {Removing redundancy from lattices},
booktitle = {15th Annual Conference of the International Speech Communication Association,
{INTERSPEECH} 2014, Singapore, September 14-18, 2014},
pages = {656--660},
publisher = {{ISCA}},
year = {2014},
url = {https://doi.org/10.21437/Interspeech.2014-166},
doi = {10.21437/INTERSPEECH.2014-166},
timestamp = {Tue, 11 Jun 2024 16:45:43 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/NoldenSPGMN14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/ChiuWTPCR14,
author = {Justin T. Chiu and
Yun Wang and
Jan Trmal and
Daniel Povey and
Guoguo Chen and
Alexander I. Rudnicky},
editor = {Haizhou Li and
Helen M. Meng and
Bin Ma and
Engsiong Chng and
Lei Xie},
title = {Combination of {FST} and {CN} search in spoken term detection},
booktitle = {15th Annual Conference of the International Speech Communication Association,
{INTERSPEECH} 2014, Singapore, September 14-18, 2014},
pages = {2784--2788},
publisher = {{ISCA}},
year = {2014},
url = {https://doi.org/10.21437/Interspeech.2014-532},
doi = {10.21437/INTERSPEECH.2014-532},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/ChiuWTPCR14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iwslt/Kumar0CCPK14,
author = {Gaurav Kumar and
Yuan Cao and
Ryan Cotterell and
Chris Callison{-}Burch and
Daniel Povey and
Sanjeev Khudanpur},
title = {Translations of the Callhome Egyptian Arabic corpus for conversational
speech translation},
booktitle = {Proceedings of the 11th International Workshop on Spoken Language
Translation: Papers, {IWSLT} 2014, Lake Tahoe, CA, USA, December 4-5,
2014},
year = {2014},
url = {https://aclanthology.org/2014.iwslt-papers.13},
timestamp = {Thu, 01 Aug 2024 15:37:24 +0200},
biburl = {https://dblp.org/rec/conf/iwslt/Kumar0CCPK14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/slt/Garcia-RomeroZM14,
author = {Daniel Garcia{-}Romero and
Xiaohui Zhang and
Alan McCree and
Daniel Povey},
title = {Improving speaker recognition performance in the domain adaptation
challenge using deep neural networks},
booktitle = {2014 {IEEE} Spoken Language Technology Workshop, {SLT} 2014, South
Lake Tahoe, NV, USA, December 7-10, 2014},
pages = {378--383},
publisher = {{IEEE}},
year = {2014},
url = {https://doi.org/10.1109/SLT.2014.7078604},
doi = {10.1109/SLT.2014.7078604},
timestamp = {Thu, 04 Apr 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/slt/Garcia-RomeroZM14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/slt/TrmalCPKGZMLJKY14,
author = {Jan Trmal and
Guoguo Chen and
Daniel Povey and
Sanjeev Khudanpur and
Pegah Ghahremani and
Xiaohui Zhang and
Vimal Manohar and
Chunxi Liu and
Aren Jansen and
Dietrich Klakow and
David Yarowsky and
Florian Metze},
title = {A keyword search system using open source software},
booktitle = {2014 {IEEE} Spoken Language Technology Workshop, {SLT} 2014, South
Lake Tahoe, NV, USA, December 7-10, 2014},
pages = {530--535},
publisher = {{IEEE}},
year = {2014},
url = {https://doi.org/10.1109/SLT.2014.7078630},
doi = {10.1109/SLT.2014.7078630},
timestamp = {Thu, 04 Apr 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/slt/TrmalCPKGZMLJKY14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/asru/ChenYTPK13,
author = {Guoguo Chen and
Oguz Yilmaz and
Jan Trmal and
Daniel Povey and
Sanjeev Khudanpur},
title = {Using proxies for {OOV} keywords in the keyword search task},
booktitle = {2013 {IEEE} Workshop on Automatic Speech Recognition and Understanding,
Olomouc, Czech Republic, December 8-12, 2013},
pages = {416--421},
publisher = {{IEEE}},
year = {2013},
url = {https://doi.org/10.1109/ASRU.2013.6707766},
doi = {10.1109/ASRU.2013.6707766},
timestamp = {Wed, 16 Oct 2019 14:14:51 +0200},
biburl = {https://dblp.org/rec/conf/asru/ChenYTPK13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/HannemannPZ13,
author = {Mirko Hannemann and
Daniel Povey and
Geoffrey Zweig},
title = {Combining forward and backward search in decoding},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2013, Vancouver, BC, Canada, May 26-31, 2013},
pages = {6739--6743},
publisher = {{IEEE}},
year = {2013},
url = {https://doi.org/10.1109/ICASSP.2013.6638966},
doi = {10.1109/ICASSP.2013.6638966},
timestamp = {Wed, 16 Oct 2019 14:14:52 +0200},
biburl = {https://dblp.org/rec/conf/icassp/HannemannPZ13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/MotlicekPK13,
author = {Petr Motl{\'{\i}}cek and
Daniel Povey and
Martin Karafi{\'{a}}t},
title = {Feature and score level combination of subspace Gaussinas in {LVCSR}
task},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2013, Vancouver, BC, Canada, May 26-31, 2013},
pages = {7604--7608},
publisher = {{IEEE}},
year = {2013},
url = {https://doi.org/10.1109/ICASSP.2013.6639142},
doi = {10.1109/ICASSP.2013.6639142},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/MotlicekPK13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/ChenKPTYY13,
author = {Guoguo Chen and
Sanjeev Khudanpur and
Daniel Povey and
Jan Trmal and
David Yarowsky and
Oguz Yilmaz},
title = {Quantifying the value of pronunciation lexicons for keyword search
in lowresource languages},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2013, Vancouver, BC, Canada, May 26-31, 2013},
pages = {8560--8564},
publisher = {{IEEE}},
year = {2013},
url = {https://doi.org/10.1109/ICASSP.2013.6639336},
doi = {10.1109/ICASSP.2013.6639336},
timestamp = {Fri, 19 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/ChenKPTYY13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/RathPVC13,
author = {Shakti P. Rath and
Daniel Povey and
Karel Vesel{\'{y}} and
Jan Cernock{\'{y}}},
editor = {Fr{\'{e}}d{\'{e}}ric Bimbot and
Christophe Cerisara and
C{\'{e}}cile Fougeron and
Guillaume Gravier and
Lori Lamel and
Fran{\c{c}}ois Pellegrino and
Pascal Perrier},
title = {Improved feature processing for deep neural networks},
booktitle = {14th Annual Conference of the International Speech Communication Association,
{INTERSPEECH} 2013, Lyon, France, August 25-29, 2013},
pages = {109--113},
publisher = {{ISCA}},
year = {2013},
url = {https://doi.org/10.21437/Interspeech.2013-48},
doi = {10.21437/INTERSPEECH.2013-48},
timestamp = {Tue, 11 Jun 2024 16:45:43 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/RathPVC13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/VeselyGBP13,
author = {Karel Vesel{\'{y}} and
Arnab Ghoshal and
Luk{\'{a}}s Burget and
Daniel Povey},
editor = {Fr{\'{e}}d{\'{e}}ric Bimbot and
Christophe Cerisara and
C{\'{e}}cile Fougeron and
Guillaume Gravier and
Lori Lamel and
Fran{\c{c}}ois Pellegrino and
Pascal Perrier},
title = {Sequence-discriminative training of deep neural networks},
booktitle = {14th Annual Conference of the International Speech Communication Association,
{INTERSPEECH} 2013, Lyon, France, August 25-29, 2013},
pages = {2345--2349},
publisher = {{ISCA}},
year = {2013},
url = {https://doi.org/10.21437/Interspeech.2013-548},
doi = {10.21437/INTERSPEECH.2013-548},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/VeselyGBP13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/csl/PoveyY12,
author = {Daniel Povey and
Kaisheng Yao},
title = {A basis representation of constrained {MLLR} transforms for robust
adaptation},
journal = {Comput. Speech Lang.},
volume = {26},
number = {1},
pages = {35--51},
year = {2012},
url = {https://doi.org/10.1016/j.csl.2011.04.002},
doi = {10.1016/J.CSL.2011.04.002},
timestamp = {Thu, 20 Feb 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/csl/PoveyY12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/VinyalsRP12,
author = {Oriol Vinyals and
Suman V. Ravuri and
Daniel Povey},
title = {Revisiting Recurrent Neural Networks for robust {ASR}},
booktitle = {2012 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2012, Kyoto, Japan, March 25-30, 2012},
pages = {4085--4088},
publisher = {{IEEE}},
year = {2012},
url = {https://doi.org/10.1109/ICASSP.2012.6288816},
doi = {10.1109/ICASSP.2012.6288816},
timestamp = {Wed, 16 Oct 2019 14:14:52 +0200},
biburl = {https://dblp.org/rec/conf/icassp/VinyalsRP12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/PoveyHBBGJKKMQRVV12,
author = {Daniel Povey and
Mirko Hannemann and
Gilles Boulianne and
Luk{\'{a}}s Burget and
Arnab Ghoshal and
Milos Janda and
Martin Karafi{\'{a}}t and
Stefan Kombrink and
Petr Motl{\'{\i}}cek and
Yanmin Qian and
Korbinian Riedhammer and
Karel Vesel{\'{y}} and
Ngoc Thang Vu},
title = {Generating exact lattices in the {WFST} framework},
booktitle = {2012 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2012, Kyoto, Japan, March 25-30, 2012},
pages = {4213--4216},
publisher = {{IEEE}},
year = {2012},
url = {https://doi.org/10.1109/ICASSP.2012.6288848},
doi = {10.1109/ICASSP.2012.6288848},
timestamp = {Mon, 05 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/PoveyHBBGJKKMQRVV12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/VuSP12,
author = {Ngoc Thang Vu and
Tanja Schultz and
Daniel Povey},
title = {Modeling gender dependency in the Subspace {GMM} framework},
booktitle = {2012 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2012, Kyoto, Japan, March 25-30, 2012},
pages = {4345--4348},
publisher = {{IEEE}},
year = {2012},
url = {https://doi.org/10.1109/ICASSP.2012.6288881},
doi = {10.1109/ICASSP.2012.6288881},
timestamp = {Sat, 31 Jul 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/VuSP12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/RiedhammerBGP12,
author = {Korbinian Riedhammer and
Tobias Bocklet and
Arnab Ghoshal and
Daniel Povey},
title = {Revisiting semi-continuous hidden Markov models},
booktitle = {2012 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2012, Kyoto, Japan, March 25-30, 2012},
pages = {4721--4724},
publisher = {{IEEE}},
year = {2012},
url = {https://doi.org/10.1109/ICASSP.2012.6288973},
doi = {10.1109/ICASSP.2012.6288973},
timestamp = {Mon, 05 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/RiedhammerBGP12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/WengJP12,
author = {Chao Weng and
Biing{-}Hwang Juang and
Daniel Povey},
title = {Discriminative Training Using Non-uniform Criteria for Keyword Spotting
on Spontaneous Speech},
booktitle = {13th Annual Conference of the International Speech Communication Association,
{INTERSPEECH} 2012, Portland, Oregon, USA, September 9-13, 2012},
pages = {559--562},
publisher = {{ISCA}},
year = {2012},
url = {https://doi.org/10.21437/Interspeech.2012-172},
doi = {10.21437/INTERSPEECH.2012-172},
timestamp = {Tue, 11 Jun 2024 16:45:43 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/WengJP12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:journals/jmlr/VinyalsP12,
author = {Oriol Vinyals and
Daniel Povey},
editor = {Neil D. Lawrence and
Mark A. Girolami},
title = {Krylov Subspace Descent for Deep Learning},
booktitle = {Proceedings of the Fifteenth International Conference on Artificial
Intelligence and Statistics, {AISTATS} 2012, La Palma, Canary Islands,
Spain, April 21-23, 2012},
series = {{JMLR} Proceedings},
volume = {22},
pages = {1261--1268},
publisher = {JMLR.org},
year = {2012},
url = {http://proceedings.mlr.press/v22/vinyals12.html},
timestamp = {Wed, 29 May 2019 08:41:44 +0200},
biburl = {https://dblp.org/rec/journals/jmlr/VinyalsP12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/csl/PoveyBAAKGGGKRRST11,
author = {Daniel Povey and
Luk{\'{a}}s Burget and
Mohit Agarwal and
Pinar Akyazi and
Kai Feng and
Arnab Ghoshal and
Ondrej Glembek and
Nagendra K. Goel and
Martin Karafi{\'{a}}t and
Ariya Rastrow and
Richard C. Rose and
Petr Schwarz and
Samuel Thomas},
title = {The subspace Gaussian mixture model - {A} structured model for speech
recognition},
journal = {Comput. Speech Lang.},
volume = {25},
number = {2},
pages = {404--439},
year = {2011},
url = {https://doi.org/10.1016/j.csl.2010.06.003},
doi = {10.1016/J.CSL.2010.06.003},
timestamp = {Thu, 24 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/csl/PoveyBAAKGGGKRRST11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/csl/XuPMZ11,
author = {Haihua Xu and
Daniel Povey and
Lidia Mangu and
Jie Zhu},
title = {Minimum Bayes Risk decoding and system combination based on a recursion
for edit distance},
journal = {Comput. Speech Lang.},
volume = {25},
number = {4},
pages = {802--828},
year = {2011},
url = {https://doi.org/10.1016/j.csl.2011.03.001},
doi = {10.1016/J.CSL.2011.03.001},
timestamp = {Thu, 20 Feb 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/csl/XuPMZ11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/asru/PoveyZA11,
author = {Daniel Povey and
Geoffrey Zweig and
Alex Acero},
editor = {David Nahamoo and
Michael Picheny},
title = {Speaker adaptation with an Exponential Transform},
booktitle = {2011 {IEEE} Workshop on Automatic Speech Recognition {\&} Understanding,
{ASRU} 2011, Waikoloa, HI, USA, December 11-15, 2011},
pages = {158--163},
publisher = {{IEEE}},
year = {2011},
url = {https://doi.org/10.1109/ASRU.2011.6163923},
doi = {10.1109/ASRU.2011.6163923},
timestamp = {Wed, 16 Oct 2019 14:14:51 +0200},
biburl = {https://dblp.org/rec/conf/asru/PoveyZA11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/asru/MikolovDPBC11,
author = {Tom{\'{a}}s Mikolov and
Anoop Deoras and
Daniel Povey and
Luk{\'{a}}s Burget and
Jan Cernock{\'{y}}},
editor = {David Nahamoo and
Michael Picheny},
title = {Strategies for training large scale neural network language models},
booktitle = {2011 {IEEE} Workshop on Automatic Speech Recognition {\&} Understanding,
{ASRU} 2011, Waikoloa, HI, USA, December 11-15, 2011},
pages = {196--201},
publisher = {{IEEE}},
year = {2011},
url = {https://doi.org/10.1109/ASRU.2011.6163930},
doi = {10.1109/ASRU.2011.6163930},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/asru/MikolovDPBC11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/asru/QianXPL11,
author = {Yanmin Qian and
Ji Xu and
Daniel Povey and
Jia Liu},
editor = {David Nahamoo and
Michael Picheny},
title = {Strategies for using {MLP} based features with limited target-language
training data},
booktitle = {2011 {IEEE} Workshop on Automatic Speech Recognition {\&} Understanding,
{ASRU} 2011, Waikoloa, HI, USA, December 11-15, 2011},
pages = {354--358},
publisher = {{IEEE}},
year = {2011},
url = {https://doi.org/10.1109/ASRU.2011.6163957},
doi = {10.1109/ASRU.2011.6163957},
timestamp = {Mon, 20 Apr 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/asru/QianXPL11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/PoveyY11,
author = {Daniel Povey and
Kaisheng Yao},
title = {A basis method for robust estimation of constrained {MLLR}},
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 = {4460--4463},
publisher = {{IEEE}},
year = {2011},
url = {https://doi.org/10.1109/ICASSP.2011.5947344},
doi = {10.1109/ICASSP.2011.5947344},
timestamp = {Fri, 19 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/PoveyY11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/PoveyKGS11,
author = {Daniel Povey and
Martin Karafi{\'{a}}t and
Arnab Ghoshal and
Petr Schwarz},
title = {A symmetrization of the Subspace Gaussian Mixture Model},
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 = {4504--4507},
publisher = {{IEEE}},
year = {2011},
url = {https://doi.org/10.1109/ICASSP.2011.5947355},
doi = {10.1109/ICASSP.2011.5947355},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/PoveyKGS11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/QianPL11,
author = {Yanmin Qian and
Daniel Povey and
Jia Liu},
title = {State-Level Data Borrowing for Low-Resource Speech Recognition Based
on Subspace GMMs},
booktitle = {12th Annual Conference of the International Speech Communication Association,
{INTERSPEECH} 2011, Florence, Italy, August 27-31, 2011},
pages = {553--560},
publisher = {{ISCA}},
year = {2011},
url = {https://doi.org/10.21437/Interspeech.2011-229},
doi = {10.21437/INTERSPEECH.2011-229},
timestamp = {Tue, 11 Jun 2024 16:45:43 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/QianPL11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/ChuP10,
author = {Stephen M. Chu and
Daniel Povey},
title = {Speaking rate adaptation using continuous frame rate normalization},
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 = {4306--4309},
publisher = {{IEEE}},
year = {2010},
url = {https://doi.org/10.1109/ICASSP.2010.5495656},
doi = {10.1109/ICASSP.2010.5495656},
timestamp = {Fri, 19 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/ChuP10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/GhoshalPAABFGGKRRST10,
author = {Arnab Ghoshal and
Daniel Povey and
Mohit Agarwal and
Pinar Akyazi and
Luk{\'{a}}s Burget and
Kai Feng and
Ondrej Glembek and
Nagendra Goel and
Martin Karafi{\'{a}}t and
Ariya Rastrow and
Richard C. Rose and
Petr Schwarz and
Samuel Thomas},
title = {A novel estimation of feature-space {MLLR} for full-covariance models},
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 = {4310--4313},
publisher = {{IEEE}},
year = {2010},
url = {https://doi.org/10.1109/ICASSP.2010.5495657},
doi = {10.1109/ICASSP.2010.5495657},
timestamp = {Thu, 24 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/GhoshalPAABFGGKRRST10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/PoveyBAAFGGGKRRST10,
author = {Daniel Povey and
Luk{\'{a}}s Burget and
Mohit Agarwal and
Pinar Akyazi and
Kai Feng and
Arnab Ghoshal and
Ondrej Glembek and
Nagendra K. Goel and
Martin Karafi{\'{a}}t and
Ariya Rastrow and
Richard C. Rose and
Petr Schwarz and
Samuel Thomas},
title = {Subspace Gaussian Mixture Models for speech recognition},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing, {ICASSP} 2010, 14-19 March 2010, Sheraton Dallas
Hotel, Dallas, Texas, {USA}},
pages = {4330--4333},
publisher = {{IEEE}},
year = {2010},
url = {https://doi.org/10.1109/ICASSP.2010.5495662},
doi = {10.1109/ICASSP.2010.5495662},
timestamp = {Thu, 24 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/PoveyBAAFGGGKRRST10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/BurgetSAAFGGGKPRRT10,
author = {Luk{\'{a}}s Burget and
Petr Schwarz and
Mohit Agarwal and
Pinar Akyazi and
Kai Feng and
Arnab Ghoshal and
Ondrej Glembek and
Nagendra K. Goel and
Martin Karafi{\'{a}}t and
Daniel Povey and
Ariya Rastrow and
Richard C. Rose and
Samuel Thomas},
title = {Multilingual acoustic modeling for speech recognition based on subspace
Gaussian Mixture Models},
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 = {4334--4337},
publisher = {{IEEE}},
year = {2010},
url = {https://doi.org/10.1109/ICASSP.2010.5495646},
doi = {10.1109/ICASSP.2010.5495646},
timestamp = {Thu, 24 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/BurgetSAAFGGGKPRRT10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/ChuPKMZSQ10,
author = {Stephen M. Chu and
Daniel Povey and
Hong{-}Kwang Kuo and
Lidia Mangu and
Shilei Zhang and
Qin Shi and
Yong Qin},
title = {The 2009 {IBM} {GALE} Mandarin broadcast transcription system},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing, {ICASSP} 2010, 14-19 March 2010, Sheraton Dallas
Hotel, Dallas, Texas, {USA}},
pages = {4374--4377},
publisher = {{IEEE}},
year = {2010},
url = {https://doi.org/10.1109/ICASSP.2010.5495639},
doi = {10.1109/ICASSP.2010.5495639},
timestamp = {Thu, 23 Nov 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/ChuPKMZSQ10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/SaonSCCKKMP10,
author = {George Saon and
Hagen Soltau and
Upendra V. Chaudhari and
Stephen M. Chu and
Brian Kingsbury and
Hong{-}Kwang Kuo and
Lidia Mangu and
Daniel Povey},
title = {The {IBM} 2008 {GALE} Arabic speech transcription system},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing, {ICASSP} 2010, 14-19 March 2010, Sheraton Dallas
Hotel, Dallas, Texas, {USA}},
pages = {4378--4381},
publisher = {{IEEE}},
year = {2010},
url = {https://doi.org/10.1109/ICASSP.2010.5495640},
doi = {10.1109/ICASSP.2010.5495640},
timestamp = {Fri, 19 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/SaonSCCKKMP10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/XuPMZ10,
author = {Haihua Xu and
Daniel Povey and
Lidia Mangu and
Jie Zhu},
title = {An improved consensus-like method for Minimum Bayes Risk decoding
and lattice combination},
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 = {4938--4941},
publisher = {{IEEE}},
year = {2010},
url = {https://doi.org/10.1109/ICASSP.2010.5495100},
doi = {10.1109/ICASSP.2010.5495100},
timestamp = {Thu, 19 Dec 2019 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/XuPMZ10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/GoelTAABFGGKPRRS10,
author = {Nagendra Goel and
Samuel Thomas and
Mohit Agarwal and
Pinar Akyazi and
Luk{\'{a}}s Burget and
Kai Feng and
Arnab Ghoshal and
Ondrej Glembek and
Martin Karafi{\'{a}}t and
Daniel Povey and
Ariya Rastrow and
Richard C. Rose and
Petr Schwarz},
title = {Approaches to automatic lexicon learning with limited training examples},
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 = {5094--5097},
publisher = {{IEEE}},
year = {2010},
url = {https://doi.org/10.1109/ICASSP.2010.5495037},
doi = {10.1109/ICASSP.2010.5495037},
timestamp = {Thu, 24 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/GoelTAABFGGKPRRS10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/taslp/SoltauSKKMPE09,
author = {Hagen Soltau and
George Saon and
Brian Kingsbury and
Hong{-}Kwang Jeff Kuo and
Lidia Mangu and
Daniel Povey and
Ahmad Emami},
title = {Advances in Arabic Speech Transcription at {IBM} Under the {DARPA}
{GALE} Program},
journal = {{IEEE} Trans. Speech Audio Process.},
volume = {17},
number = {5},
pages = {884--894},
year = {2009},
url = {https://doi.org/10.1109/TASL.2009.2022966},
doi = {10.1109/TASL.2009.2022966},
timestamp = {Sun, 17 May 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/taslp/SoltauSKKMPE09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/SaonPS09,
author = {George Saon and
Daniel Povey and
Hagen Soltau},
title = {Large margin semi-tied covariance transforms for discriminative training},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing, {ICASSP} 2009, 19-24 April 2009, Taipei, Taiwan},
pages = {3753--3756},
publisher = {{IEEE}},
year = {2009},
url = {https://doi.org/10.1109/ICASSP.2009.4960443},
doi = {10.1109/ICASSP.2009.4960443},
timestamp = {Thu, 23 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/SaonPS09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/XuPZW09,
author = {Haihua Xu and
Daniel Povey and
Jie Zhu and
Guanyong Wu},
title = {Minimum hypothesis phone error as a decoding method for speech recognition},
booktitle = {10th Annual Conference of the International Speech Communication Association,
{INTERSPEECH} 2009, Brighton, United Kingdom, September 6-10, 2009},
pages = {76--79},
publisher = {{ISCA}},
year = {2009},
url = {https://doi.org/10.21437/Interspeech.2009-17},
doi = {10.21437/INTERSPEECH.2009-17},
timestamp = {Tue, 11 Jun 2024 16:45:43 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/XuPZW09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/PoveyKKRSV08,
author = {Daniel Povey and
Dimitri Kanevsky and
Brian Kingsbury and
Bhuvana Ramabhadran and
George Saon and
Karthik Visweswariah},
title = {Boosted {MMI} for model and feature-space discriminative training},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing, {ICASSP} 2008, March 30 - April 4, 2008, Caesars
Palace, Las Vegas, Nevada, {USA}},
pages = {4057--4060},
publisher = {{IEEE}},
year = {2008},
url = {https://doi.org/10.1109/ICASSP.2008.4518545},
doi = {10.1109/ICASSP.2008.4518545},
timestamp = {Fri, 19 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/PoveyKKRSV08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/VaradarajanPC08,
author = {Balakrishnan Varadarajan and
Daniel Povey and
Selina M. Chu},
title = {Quick fmllr for speaker adaptation in speech recognition},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing, {ICASSP} 2008, March 30 - April 4, 2008, Caesars
Palace, Las Vegas, Nevada, {USA}},
pages = {4297--4300},
publisher = {{IEEE}},
year = {2008},
url = {https://doi.org/10.1109/ICASSP.2008.4518605},
doi = {10.1109/ICASSP.2008.4518605},
timestamp = {Fri, 19 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/VaradarajanPC08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/PoveyCV08,
author = {Daniel Povey and
Selina M. Chu and
Balakrishnan Varadarajan},
title = {Universal background model based speech recognition},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing, {ICASSP} 2008, March 30 - April 4, 2008, Caesars
Palace, Las Vegas, Nevada, {USA}},
pages = {4561--4564},
publisher = {{IEEE}},
year = {2008},
url = {https://doi.org/10.1109/ICASSP.2008.4518671},
doi = {10.1109/ICASSP.2008.4518671},
timestamp = {Fri, 19 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/PoveyCV08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/SaonP08,
author = {George Saon and
Daniel Povey},
title = {Penalty function maximization for large margin {HMM} training},
booktitle = {9th Annual Conference of the International Speech Communication Association,
{INTERSPEECH} 2008, Brisbane, Australia, September 22-26, 2008},
pages = {920--923},
publisher = {{ISCA}},
year = {2008},
url = {https://doi.org/10.21437/Interspeech.2008-108},
doi = {10.21437/INTERSPEECH.2008-108},
timestamp = {Tue, 11 Jun 2024 16:45:43 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/SaonP08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/PoveyKS08,
author = {Daniel Povey and
Hong{-}Kwang Jeff Kuo and
Hagen Soltau},
title = {Fast speaker adaptive training for speech recognition},
booktitle = {9th Annual Conference of the International Speech Communication Association,
{INTERSPEECH} 2008, Brisbane, Australia, September 22-26, 2008},
pages = {1245--1248},
publisher = {{ISCA}},
year = {2008},
url = {https://doi.org/10.21437/Interspeech.2008-377},
doi = {10.21437/INTERSPEECH.2008-377},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/PoveyKS08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/PoveyK08,
author = {Daniel Povey and
Brian Kingsbury},
title = {Monte Carlo model-space noise adaptation for speech recognition},
booktitle = {9th Annual Conference of the International Speech Communication Association,
{INTERSPEECH} 2008, Brisbane, Australia, September 22-26, 2008},
pages = {1281--1284},
publisher = {{ISCA}},
year = {2008},
url = {https://doi.org/10.21437/Interspeech.2008-308},
doi = {10.21437/INTERSPEECH.2008-308},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/PoveyK08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/PoveyK08a,
author = {Daniel Povey and
Hong{-}Kwang Jeff Kuo},
title = {{XMLLR} for improved speaker adaptation in speech recognition},
booktitle = {9th Annual Conference of the International Speech Communication Association,
{INTERSPEECH} 2008, Brisbane, Australia, September 22-26, 2008},
pages = {1705--1708},
publisher = {{ISCA}},
year = {2008},
url = {https://doi.org/10.21437/Interspeech.2008-380},
doi = {10.21437/INTERSPEECH.2008-380},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/PoveyK08a.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/PoveyK07,
author = {Daniel Povey and
Brian Kingsbury},
title = {Evaluation of Proposed Modifications to {MPE} for Large Scale Discriminative
Training},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing, {ICASSP} 2007, Honolulu, Hawaii, USA, April
15-20, 2007},
pages = {321--324},
publisher = {{IEEE}},
year = {2007},
url = {https://doi.org/10.1109/ICASSP.2007.366914},
doi = {10.1109/ICASSP.2007.366914},
timestamp = {Mon, 22 Jun 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/PoveyK07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/SoltauSKKMPZ07,
author = {Hagen Soltau and
George Saon and
Brian Kingsbury and
Hong{-}Kwang Jeff Kuo and
Lidia Mangu and
Daniel Povey and
Geoffrey Zweig},
title = {The {IBM} 2006 Gale Arabic {ASR} System},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing, {ICASSP} 2007, Honolulu, Hawaii, USA, April
15-20, 2007},
pages = {349--352},
publisher = {{IEEE}},
year = {2007},
url = {https://doi.org/10.1109/ICASSP.2007.366921},
doi = {10.1109/ICASSP.2007.366921},
timestamp = {Mon, 22 Jun 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/SoltauSKKMPZ07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/SarikayaZPAG07,
author = {Ruhi Sarikaya and
Bowen Zhou and
Daniel Povey and
Mohamed Afify and
Yuqing Gao},
title = {The Impact of {ASR} on Speech-to-Speech Translation Performance},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing, {ICASSP} 2007, Honolulu, Hawaii, USA, April
15-20, 2007},
pages = {1289--1292},
publisher = {{IEEE}},
year = {2007},
url = {https://doi.org/10.1109/ICASSP.2007.367313},
doi = {10.1109/ICASSP.2007.367313},
timestamp = {Mon, 22 Jun 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/SarikayaZPAG07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/taslp/HainWEGLMPW06,
author = {Thomas Hain and
Philip C. Woodland and
Gunnar Evermann and
Mark J. F. Gales and
Xunying Liu and
Gareth L. Moore and
Daniel Povey and
Lan Wang},
title = {Corrections to "Automatic Transcription of Conversational Telephone
Speech"},
journal = {{IEEE} Trans. Speech Audio Process.},
volume = {14},
number = {2},
pages = {727--727},
year = {2006},
url = {https://doi.org/10.1109/TASL.2006.871051},
doi = {10.1109/TASL.2006.871051},
timestamp = {Fri, 03 Jun 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/taslp/HainWEGLMPW06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/taslp/ChenKMPSSZ06,
author = {Stanley F. Chen and
Brian Kingsbury and
Lidia Mangu and
Daniel Povey and
George Saon and
Hagen Soltau and
Geoffrey Zweig},
title = {Advances in speech transcription at {IBM} under the {DARPA} {EARS}
program},
journal = {{IEEE} Trans. Speech Audio Process.},
volume = {14},
number = {5},
pages = {1596--1608},
year = {2006},
url = {https://doi.org/10.1109/TASL.2006.879814},
doi = {10.1109/TASL.2006.879814},
timestamp = {Sun, 17 May 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/taslp/ChenKMPSSZ06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/PelecanosPR06,
author = {Jason W. Pelecanos and
Daniel Povey and
Ganesh N. Ramaswamy},
title = {Secondary Classification for {GMM} Based Speaker Recognition},
booktitle = {2006 {IEEE} International Conference on Acoustics Speech and Signal
Processing, {ICASSP} 2006, Toulouse, France, May 14-19, 2006},
pages = {109--112},
publisher = {{IEEE}},
year = {2006},
url = {https://doi.org/10.1109/ICASSP.2006.1659969},
doi = {10.1109/ICASSP.2006.1659969},
timestamp = {Mon, 22 Jun 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/PelecanosPR06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/ZweigSSRPMK06,
author = {Geoffrey Zweig and
Olivier Siohan and
George Saon and
Bhuvana Ramabhadran and
Daniel Povey and
Lidia Mangu and
Brian Kingsbury},
title = {Automated Quality Monitoring in the Call Center with {ASR} and Maximum
Entropy},
booktitle = {2006 {IEEE} International Conference on Acoustics Speech and Signal
Processing, {ICASSP} 2006, Toulouse, France, May 14-19, 2006},
pages = {589--592},
publisher = {{IEEE}},
year = {2006},
url = {https://doi.org/10.1109/ICASSP.2006.1660089},
doi = {10.1109/ICASSP.2006.1660089},
timestamp = {Mon, 22 Jun 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/ZweigSSRPMK06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/ChoueiterPCZ06,
author = {Ghinwa F. Choueiter and
Daniel Povey and
Stanley F. Chen and
Geoffrey Zweig},
title = {Morpheme-Based Language Modeling for Arabic Lvcsr},
booktitle = {2006 {IEEE} International Conference on Acoustics Speech and Signal
Processing, {ICASSP} 2006, Toulouse, France, May 14-19, 2006},
pages = {1053--1056},
publisher = {{IEEE}},
year = {2006},
url = {https://doi.org/10.1109/ICASSP.2006.1660205},
doi = {10.1109/ICASSP.2006.1660205},
timestamp = {Mon, 22 Jun 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/ChoueiterPCZ06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/Povey06,
author = {Daniel Povey},
title = {{SPAM} and full covariance for speech recognition},
booktitle = {Ninth International Conference on Spoken Language Processing, {INTERSPEECH-ICSLP}
2006, Pittsburgh, PA, USA, September 17-21, 2006},
publisher = {{ISCA}},
year = {2006},
url = {https://doi.org/10.21437/Interspeech.2006-437},
doi = {10.21437/INTERSPEECH.2006-437},
timestamp = {Tue, 11 Jun 2024 16:45:43 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/Povey06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/PoveyS06,
author = {Daniel Povey and
George Saon},
title = {Feature and model space speaker adaptation with full covariance Gaussians},
booktitle = {Ninth International Conference on Spoken Language Processing, {INTERSPEECH-ICSLP}
2006, Pittsburgh, PA, USA, September 17-21, 2006},
publisher = {{ISCA}},
year = {2006},
url = {https://doi.org/10.21437/Interspeech.2006-349},
doi = {10.21437/INTERSPEECH.2006-349},
timestamp = {Thu, 22 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/PoveyS06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/mlmi/HuangWCSPLSSRP06,
author = {Jing Huang and
Martin Westphal and
Stanley F. Chen and
Olivier Siohan and
Daniel Povey and
Vit Libal and
Alvaro Soneiro and
Henrik Schulz and
Thomas Ross and
Gerasimos Potamianos},
editor = {Steve Renals and
Samy Bengio and
Jonathan G. Fiscus},
title = {The {IBM} Rich Transcription Spring 2006 Speech-to-Text System for
Lecture Meetings},
booktitle = {Machine Learning for Multimodal Interaction, Third International Workshop,
{MLMI} 2006, Bethesda, MD, USA, May 1-4, 2006, Revised Selected Papers},
series = {Lecture Notes in Computer Science},
volume = {4299},
pages = {432--443},
publisher = {Springer},
year = {2006},
url = {https://doi.org/10.1007/11965152\_38},
doi = {10.1007/11965152\_38},
timestamp = {Fri, 10 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/mlmi/HuangWCSPLSSRP06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/naacl/ZweigSSRPMK06,
author = {Geoffrey Zweig and
Olivier Siohan and
George Saon and
Bhuvana Ramabhadran and
Daniel Povey and
Lidia Mangu and
Brian Kingsbury},
editor = {Robert C. Moore and
Jeff A. Bilmes and
Jennifer Chu{-}Carroll and
Mark Sanderson},
title = {Automated Quality Monitoring for Call Centers using Speech and {NLP}
Technologies},
booktitle = {Human Language Technology Conference of the North American Chapter
of the Association of Computational Linguistics, Proceedings, June
4-9, 2006, New York, New York, {USA}},
publisher = {The Association for Computational Linguistics},
year = {2006},
url = {https://aclanthology.org/N06-4011/},
timestamp = {Fri, 06 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/naacl/ZweigSSRPMK06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/taslp/HainWEGLMPW05,
author = {Thomas Hain and
Philip C. Woodland and
Gunnar Evermann and
Mark J. F. Gales and
Xunying Liu and
Gareth L. Moore and
Daniel Povey and
Lan Wang},
title = {Automatic transcription of conversational telephone speech},
journal = {{IEEE} Trans. Speech Audio Process.},
volume = {13},
number = {6},
pages = {1173--1185},
year = {2005},
url = {https://doi.org/10.1109/TSA.2005.852999},
doi = {10.1109/TSA.2005.852999},
timestamp = {Fri, 09 Apr 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/taslp/HainWEGLMPW05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/SoltauKMPSZ05,
author = {Hagen Soltau and
Brian Kingsbury and
Lidia Mangu and
Daniel Povey and
George Saon and
Geoffrey Zweig},
title = {The {IBM} 2004 Conversational Telephony System for Rich Transcription},
booktitle = {2005 {IEEE} International Conference on Acoustics, Speech, and Signal
Processing, {ICASSP} '05, Philadelphia, Pennsylvania, USA, March 18-23,
2005},
pages = {205--208},
publisher = {{IEEE}},
year = {2005},
url = {https://doi.org/10.1109/ICASSP.2005.1415086},
doi = {10.1109/ICASSP.2005.1415086},
timestamp = {Mon, 22 Jun 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/SoltauKMPSZ05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/PoveyKMSSZ05,
author = {Daniel Povey and
Brian Kingsbury and
Lidia Mangu and
George Saon and
Hagen Soltau and
Geoffrey Zweig},
title = {fMPE: Discriminatively Trained Features for Speech Recognition},
booktitle = {2005 {IEEE} International Conference on Acoustics, Speech, and Signal
Processing, {ICASSP} '05, Philadelphia, Pennsylvania, USA, March 18-23,
2005},
pages = {961--964},
publisher = {{IEEE}},
year = {2005},
url = {https://doi.org/10.1109/ICASSP.2005.1415275},
doi = {10.1109/ICASSP.2005.1415275},
timestamp = {Mon, 22 Jun 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/PoveyKMSSZ05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/SaonPZ05,
author = {George Saon and
Daniel Povey and
Geoffrey Zweig},
title = {Anatomy of an extremely fast {LVCSR} decoder},
booktitle = {9th European Conference on Speech Communication and Technology, INTERSPEECH-Eurospeech
2005, Lisbon, Portugal, September 4-8, 2005},
pages = {549--552},
publisher = {{ISCA}},
year = {2005},
url = {https://doi.org/10.21437/Interspeech.2005-338},
doi = {10.21437/INTERSPEECH.2005-338},
timestamp = {Tue, 11 Jun 2024 16:45:43 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/SaonPZ05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/HuangP05,
author = {Jing Huang and
Daniel Povey},
title = {Discriminatively trained features using fMPE for multi-stream audio-visual
speech recognition},
booktitle = {9th European Conference on Speech Communication and Technology, INTERSPEECH-Eurospeech
2005, Lisbon, Portugal, September 4-8, 2005},
pages = {777--780},
publisher = {{ISCA}},
year = {2005},
url = {https://doi.org/10.21437/Interspeech.2005-361},
doi = {10.21437/INTERSPEECH.2005-361},
timestamp = {Thu, 22 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/HuangP05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/Povey05,
author = {Daniel Povey},
title = {Improvements to fMPE for discriminative training of features},
booktitle = {9th European Conference on Speech Communication and Technology, INTERSPEECH-Eurospeech
2005, Lisbon, Portugal, September 4-8, 2005},
pages = {2977--2980},
publisher = {{ISCA}},
year = {2005},
url = {https://doi.org/10.21437/Interspeech.2005-133},
doi = {10.21437/INTERSPEECH.2005-133},
timestamp = {Thu, 22 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/Povey05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/SaonDP04,
author = {George Saon and
Satya Dharanipragada and
Daniel Povey},
title = {Feature space Gaussianization},
booktitle = {2004 {IEEE} International Conference on Acoustics, Speech, and Signal
Processing, {ICASSP} 2004, Montreal, Quebec, Canada, May 17-21, 2004},
pages = {329--332},
publisher = {{IEEE}},
year = {2004},
url = {https://doi.org/10.1109/ICASSP.2004.1325989},
doi = {10.1109/ICASSP.2004.1325989},
timestamp = {Mon, 28 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/SaonDP04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/Povey04,
author = {Daniel Povey},
title = {Phone duration modeling for {LVCSR}},
booktitle = {2004 {IEEE} International Conference on Acoustics, Speech, and Signal
Processing, {ICASSP} 2004, Montreal, Quebec, Canada, May 17-21, 2004},
pages = {829--832},
publisher = {{IEEE}},
year = {2004},
url = {https://doi.org/10.1109/ICASSP.2004.1326114},
doi = {10.1109/ICASSP.2004.1326114},
timestamp = {Mon, 22 Jun 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/Povey04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/PoveyWG03,
author = {Daniel Povey and
Philip C. Woodland and
Mark J. F. Gales},
title = {Discriminative map for acoustic model adaptation},
booktitle = {2003 {IEEE} International Conference on Acoustics, Speech, and Signal
Processing, {ICASSP} '03, Hong Kong, April 6-10, 2003},
pages = {312--315},
publisher = {{IEEE}},
year = {2003},
url = {https://doi.org/10.1109/ICASSP.2003.1198780},
doi = {10.1109/ICASSP.2003.1198780},
timestamp = {Mon, 22 Jun 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/PoveyWG03.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/GalesDPW03,
author = {Mark J. F. Gales and
Yuan Dong and
Daniel Povey and
Philip C. Woodland},
title = {Porting: SwitchBoard to the VoiceMail task},
booktitle = {2003 {IEEE} International Conference on Acoustics, Speech, and Signal
Processing, {ICASSP} '03, Hong Kong, April 6-10, 2003},
pages = {536--539},
publisher = {{IEEE}},
year = {2003},
url = {https://doi.org/10.1109/ICASSP.2003.1198836},
doi = {10.1109/ICASSP.2003.1198836},
timestamp = {Mon, 22 Jun 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/GalesDPW03.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icdar/NopsuwanchaiP03,
author = {Roongroj Nopsuwanchai and
Daniel Povey},
title = {Discriminative Training for HMM-Based Offline Handwritten Character
Recognition},
booktitle = {7th International Conference on Document Analysis and Recognition
{(ICDAR} 2003), 2-Volume Set, 3-6 August 2003, Edinburgh, Scotland,
{UK}},
pages = {114--118},
publisher = {{IEEE} Computer Society},
year = {2003},
url = {https://doi.org/10.1109/ICDAR.2003.1227643},
doi = {10.1109/ICDAR.2003.1227643},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icdar/NopsuwanchaiP03.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/PoveyGKW03,
author = {Daniel Povey and
Mark J. F. Gales and
Do Yeong Kim and
Philip C. Woodland},
title = {{MMI-MAP} and {MPE-MAP} for acoustic model adaptation},
booktitle = {8th European Conference on Speech Communication and Technology, {EUROSPEECH}
2003 - {INTERSPEECH} 2003, Geneva, Switzerland, September 1-4, 2003},
pages = {1981--1984},
publisher = {{ISCA}},
year = {2003},
url = {https://doi.org/10.21437/Eurospeech.2003-572},
doi = {10.21437/EUROSPEECH.2003-572},
timestamp = {Thu, 22 Jun 2023 16:42:17 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/PoveyGKW03.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/csl/WoodlandP02,
author = {Philip C. Woodland and
Daniel Povey},
title = {Large scale discriminative training of hidden Markov models for speech
recognition},
journal = {Comput. Speech Lang.},
volume = {16},
number = {1},
pages = {25--47},
year = {2002},
url = {https://doi.org/10.1006/csla.2001.0182},
doi = {10.1006/CSLA.2001.0182},
timestamp = {Thu, 20 Feb 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/csl/WoodlandP02.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/PoveyW02,
author = {Daniel Povey and
Philip C. Woodland},
title = {Minimum Phone Error and I-smoothing for improved discriminative training},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing, {ICASSP} 2002, May 13-17 2002, Orlando, Florida,
{USA}},
pages = {105--108},
publisher = {{IEEE}},
year = {2002},
url = {https://doi.org/10.1109/ICASSP.2002.5743665},
doi = {10.1109/ICASSP.2002.5743665},
timestamp = {Wed, 16 Oct 2019 14:14:52 +0200},
biburl = {https://dblp.org/rec/conf/icassp/PoveyW02.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/PoveyW01,
author = {Daniel Povey and
Philip C. Woodland},
title = {Improved discriminative training techniques for large vocabulary continuous
speech recognition},
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 = {45--48},
publisher = {{IEEE}},
year = {2001},
url = {https://doi.org/10.1109/ICASSP.2001.940763},
doi = {10.1109/ICASSP.2001.940763},
timestamp = {Thu, 23 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/PoveyW01.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/HainWEP01,
author = {Thomas Hain and
Philip C. Woodland and
Gunnar Evermann and
Daniel Povey},
title = {New features in the {CU-HTK} system for transcription of conversational
telephone speech},
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 = {57--60},
publisher = {{IEEE}},
year = {2001},
url = {https://doi.org/10.1109/ICASSP.2001.940766},
doi = {10.1109/ICASSP.2001.940766},
timestamp = {Thu, 23 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/HainWEP01.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/PoveyW99,
author = {Daniel Povey and
Philip C. Woodland},
title = {Frame discrimination training for HMMs for large vocabulary speech
recognition},
booktitle = {Proceedings of the 1999 {IEEE} International Conference on Acoustics,
Speech, and Signal Processing, {ICASSP} '99, Phoenix, Arizona, USA,
March 15-19, 1999},
pages = {333--336},
publisher = {{IEEE} Computer Society},
year = {1999},
url = {https://doi.org/10.1109/ICASSP.1999.758130},
doi = {10.1109/ICASSP.1999.758130},
timestamp = {Thu, 23 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/PoveyW99.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
last updated on 2024-08-25 19:11 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:
