publications.bib

% List of all Lingvo publications, grouped by topic, and listed in
% chronological order with the newest papers on the bottom of each group.

% Common conferences.
@string{acl = {Proc. Annual Meeting of the Association for Computational Linguistics ({ACL})}}
@string{emnlp = {Proc. Conference on Empirical Methods in Natural Language Processing ({EMNLP})}}
@string{icassp = {Proc. {IEEE} International Conference on Acoustics, Speech, and Signal Processing ({ICASSP})}}
@string{iclr = {Proc. International Conference on Learning Representations ({ICLR})}}
@string{icml = {Proc. International Conference on Machine Learning ({ICML})}}
@string{interspeech = {Proc. Interspeech}}
@string{naacl = {Proc. Conference of the North American Chapter of the Association for Computational Linguistics ({NAACL})}}
@string{nips = {Advances in Neural Information Processing Systems}}
@string{slt = {Proc. {IEEE} Spoken Language Technology Workshop ({SLT})}}
@string{asru = {Proc. {IEEE} Automatic Speech Recognition and Understanding Workshop ({ASRU})}}
@string{odyssey = {Odyssey: The Speaker and Language Recognition Workshop}}

% Topic annotations, used by update_publications.sh to update the markdown index.
@string{nmt = {Translation}}
@string{tts = {Speech synthesis}}
@string{asr = {Speech recognition}}
@string{st = {Speech translation}}
@string{enhancement = {Speech enhancement}}
@string{nlu = {Language understanding}}
@string{opt = {Optimization}}
@string{slr = {Speaker and language recognition}}

%%%%%%%%%%%%%%%%%%%%
% Translation papers.

@techreport{wu2016google,
  annote = nmt,
  title = {Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation},
  author = {Y. Wu and M. Schuster and Z. Chen and Q. V. Le and M. Norouzi and W. Macherey and M. Krikun and Y. Cao and Q. Gao and K. Macherey and J. Klingner and A. Shah and M. Johnson and X. Liu and \L. Kaiser and S. Gouws and Y. Kato and T. Kudo and H. Kazawa and K. Stevens and G. Kurian and N. Patil and W. Wang and C. Young and J. Smith and J. Riesa and A. Rudnick and O. Vinyals and G. Corrado and M. Hughes and J. Dean},
  year = {2016},
  pdf = {https://arxiv.org/abs/1609.08144},
}

@article{johnson-etal-2017-googles,
  annote = nmt,
    title = "{G}oogle{'}s Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation",
    author = "Johnson, Melvin  and
      Schuster, Mike  and
      Le, Quoc V.  and
      Krikun, Maxim  and
      Wu, Yonghui  and
      Chen, Zhifeng  and
      Thorat, Nikhil  and
      Vi{\'e}gas, Fernanda  and
      Wattenberg, Martin  and
      Corrado, Greg  and
      Hughes, Macduff  and
      Dean, Jeffrey",
    journal = "Transactions of the Association for Computational Linguistics",
    volume = "5",
    year = "2017",
    pdf = "https://www.aclweb.org/anthology/Q17-1024",
    doi = "10.1162/tacl_a_00065",
    pages = "339--351",
}

@article{eriguchi2018zero,
  annote = nmt,
  title={Zero-Shot Cross-lingual Classification Using Multilingual Neural Machine Translation},
  author={Eriguchi, Akiko and Johnson, Melvin and Firat, Orhan and Kazawa, Hideto and Macherey, Wolfgang},
  journal={arXiv preprint arXiv:1809.04686},
  year={2018},
  pdf={https://arxiv.org/abs/1809.04686},
}

@inproceedings{bapna2018training,
  annote = nmt,
  author = {A. Bapna and M. X. Chen and O. Firat and Y. Cao and Y. Wu},
  title = {Training Deeper Neural Machine Translation Models with Transparent Attention},
  booktitle = emnlp,
  year = {2018},
  pdf = {https://arxiv.org/abs/1808.07561},
}

@inproceedings{cherry2018revisiting,
  annote = nmt,
  author = {C. Cherry and G. Foster and A. Bapna and O. Firat and W. Macherey},
  title = {Revisiting Character-Based Neural Machine Translation with Capacity and Compression},
  booktitle = emnlp,
  year = {2018},
  pdf = {https://arxiv.org/abs/1808.09943},
}

@inproceedings{chen2018best,
  annote = nmt,
  author = {M. X. Chen and O. Firat and A. Bapna and M. Johnson and W. Macherey and G. Foster and L. Jones and M. Schuster and N. Shazeer and N. Parmar and A. Vaswani and J. Uszkoreit and L. Kaiser and Z. Chen and Y. Wu and M. Hughes},
  title = {{The Best of Both Worlds: Combining Recent Advances in Neural Machine Translation}},
  booktitle = acl,
  year = {2018},
  pdf = {https://arxiv.org/abs/1804.09849},
}

@article{kuczmarski2018gender,
  annote = nmt,
  title={Gender-Aware Natural Language Translation},
  author={J. Kuczmarski and M. Johnson},
  year={2018},
  pdf = {https://www.tdcommons.org/dpubs_series/1577/},
}

@article{aharoni2019massively,
  annote = nmt,
  title={Massively Multilingual Neural Machine Translation},
  author={R. Aharoni and M. Johnson and O. Firat},
  booktitle = naacl,
  year={2019},
  pdf = {https://arxiv.org/abs/1903.00089},
}

@article{luo2019neural,
  annote = nmt,
  title={Neural Decipherment via Minimum-Cost Flow: From Ugaritic to Linear B},
  author={J. Luo and Y. Cao and R. Barzilay},
  booktitle = acl,
  year={2019},
  url = {https://www.aclweb.org/anthology/P19-1303/},
}


@inproceedings{milk,
    annote = nmt,
    title={Monotonic Infinite Lookback Attention for Simultaneous Machine Translation},
    author={Naveen Arivazhagan and Colin Cherry and Wolfgang Macherey and Chung-Cheng Chiu and Semih Yavuz and Ruoming Pang and Wei Li and Colin Raffel},
    booktitle = acl,
    year={2019},
    url = {https://arxiv.org/abs/1906.05218}
}

@article{freitag2019text,
  annote = nmt,
  author = {M. Freitag and I. Caswell and S. Roy},
  title = {APE at Scale and Its Implications on MT Evaluation Biases},
  booktitle = {Proceedings of the Fourth Conference on Machine Translation (Volume 1: Research Papers)},
  publisher = {Association for Computational Linguistics},
  url = {https://www.aclweb.org/anthology/W19-5204},
  year = {2019},
  pdf = {https://arxiv.org/abs/1904.04790},
}

@article{arivazhagan2019,
  annote = nmt,
  author = {N. Arivazhagan and A. Bapna and O. Firat and D. Lepikhin and M. Johnson and M. Krikun and M. X. Chen and Y. Cao and G. Foster and C. Cherry and W. Macherey and Z. Chen and Y. Wu},
  title = {Massively Multilingual Neural Machine Translation in the Wild: Findings and Challenges},
  year      = {2019},
  url       = {http://arxiv.org/abs/1907.05019},
  archivePrefix = {arXiv},
  eprint    = {1907.05019},
}

@incollection{huang2019gpipe,
  annote = nmt,
  author = {Y. Huang and Y. Cheng and A. Bapna and O. Firat and M. X. Chen and D. Chen and H. Lee and J. Ngiam and Q. V. Le and Y. Wu and Z. Chen},
  title = {GPipe: Efficient Training of Giant Neural Networks using Pipeline Parallelism},
  booktitle = nips,
  year = {2019},
  url = {https://arxiv.org/abs/1811.06965}
}


%%%%%%%%%%%%%%%%%%%%
% Speech recognition papers.

@inproceedings{chiu2018state,
  annote = asr,
  title = {State-of-the-art Speech Recognition With Sequence-to-Sequence Models},
  author = {C.-C.Chiu and T. N. Sainath and Y. Wu and R. Prabhavalkar and P. Nguyen and Z. Chen and A. Kannan and R. J. Weiss and K. Rao and K. Gonina and N. Jaitly and B. Li and J. Chorowski and M. Bacchiani},
  booktitle = icassp,
  year = {2018},
  pdf = {https://arxiv.org/abs/1712.01769},
}

@inproceedings{toshniwal2018multilingual,
  annote = asr,
  title = {Multilingual Speech Recognition With A Single End-To-End Model},
  author = {S. Toshniwal and T. N. Sainath and R. J. Weiss and B. Li and P. Moreno and E. Weinstein and K. Rao},
  booktitle = icassp,
  year = {2018},
  pdf = {https://arxiv.org/abs/1711.01694},
}

@inproceedings{li2018multidialect,
  annote = asr,
  title = {{Multi-Dialect Speech Recognition With a Single Sequence-to-Sequence Model}},
  author = {B. Li and T. N. Sainath and K. Sim and M. Bacchiani and E. Weinstein and P. Nguyen and Z. Chen and Y. Wu and K. Rao},
  booktitle = icassp,
  year = {2018},
  pdf = {https://arxiv.org/abs/1712.01541},
}

@inproceedings{sainath2018no,
  annote = asr,
  title = {{No Need for a Lexicon? Evaluating the Value of the Pronunciation Lexica in End-to-End Models}},
  author = {T. N. Sainath and P. Prabhavalkar and S. Kumar and S. Lee and A. Kannan and D. Rybach and V. Schogol and P. Nguyen and B. Li and Y. Wu and Z. Chen and C. C. Chiu},
  booktitle = icassp,
  year = {2018},
  pdf = {https://arxiv.org/abs/1712.01864},
}

@inproceedings{lawson2018learning,
  annote = asr,
  title = {{Learning hard alignments with variational inference}},
  author = {D. Lawson and C. C. Chiu and G. Tucker and C. Raffel and K. Swersky and N. Jaitly},
  booktitle = icassp,
  year = {2018},
  pdf = {https://arxiv.org/abs/1705.05524},
}

@inproceedings{kannan2018analysis,
  annote = asr,
  title = {An Analysis of Incorporating an External Language Model into a Sequence-to-Sequence Model},
  author = {A. Kannan and Y. Wu and P. Nguyen and T. N. Sainath and Z. Chen and R. Prabhavalkar},
  booktitle = icassp,
  year = {2018},
  pdf = {https://arxiv.org/abs/1712.01996},
}

@inproceedings{prabhavalkar2018minimum,
  annote = asr,
  author = {R. Prabhavalkar and T. N. Sainath and Y. Wu and P. Nguyen and Z. Chen and C. C. Chiu and A. Kannan},
  title = {{Minimum Word Error Rate Training for Attention-based Sequence-to-sequence Models}},
  booktitle = icassp,
  year = {2018},
  pdf = {https://arxiv.org/abs/1712.01818},
}

@inproceedings{sainath2018improving,
  annote = asr,
  title = {{Improving the Performance of Online Neural Transducer Models}},
  author = {T. N. Sainath and C. C. Chiu and R. Prabhavalkar and A. Kannan and Y. Wu and P. Nguyen and Z. Chen Z},
  booktitle = icassp,
  year = {2018},
  pdf = {https://arxiv.org/abs/1712.01807},
}

@inproceedings{chiu2018monotonic,
  annote = asr,
  title = {{Monotonic Chunkwise Attention}},
  author = {C. C. Chiu and C. Raffel},
  booktitle = iclr,
  year = {2018},
  pdf = {https://arxiv.org/abs/1712.05382},
}

@inproceedings{williams2018contextual,
  annote = asr,
  title = {{Contextual Speech Recognition in End-to-End Neural Network Systems using Beam Search}},
  author = {I. Williams and A. Kannan and P. Aleksic and D. Rybach and T. N. Sainath TN},
  booktitle = interspeech,
  year = {2018},
  pdf = {https://www.isca-speech.org/archive/Interspeech_2018/pdfs/2416.pdf},
}

@inproceedings{chui2018speech,
  annote = asr,
  title = {{Speech recognition for medical conversations}},
  author = {C. C. Chiu and A. Tripathi and K. Chou and C. Co and N. Jaitly and D. Jaunzeikare and A. Kannan and P. Nguyen and H. Sak and A. Sankar and J. Tansuwan and N. Wan and Y. Wu and X. Zhang},
  booktitle = interspeech,
  year = {2018},
  pdf = {https://arxiv.org/abs/1711.07274},
}

@inproceedings{pang2018compression,
  annote = asr,
  title = {{Compression of End-to-End Models}},
  author = {R. Pang and T. N. Sainath and R. Prabhavalkar and S. Gupta and Y. Wu and S. Zhang and C. C. Chiu},
  booktitle = interspeech,
  year = {2018},
  pdf = {https://www.isca-speech.org/archive/Interspeech_2018/pdfs/1025.pdf},
}

@inproceedings{toshniwal2018comparison,
  annote = asr,
  title = {A comparison of techniques for language model integration in encoder-decoder speech recognition},
  author = {S. Toshniwal and A. Kannan and C. C. Chiu and Y. Wu and T. N. Sainath and K. Livescu},
  booktitle = slt,
  year = {2018},
  pdf = {https://arxiv.org/abs/1807.10857},
}

@inproceedings{pundak2018deep,
  annote = asr,
  title = {Deep Context: End-to-End Contextual Speech Recognition},
  author = {G. Pundak and T. N. Sainath and R. Prabhavalkar and A. Kannan and D. Zhao},
  booktitle = slt,
  year = {2018},
  pdf = {https://arxiv.org/abs/1808.02480},
}

@inproceedings{li2019bytes,
  annote = asr,
  author = {B. Li and Y. Zhang and T. N. Sainath and Y. Wu and W. Chan},
  title = {Bytes are All You Need: End-to-End Multilingual Speech Recognition and Synthesis with Bytes},
  booktitle = icassp,
  year = {2019},
  pdf = {https://arxiv.org/abs/1811.09021},
}

@inproceedings{guo2019spelling,
  annote = asr,
  author = {J. Guo and T. N. Sainath and R. J. Weiss},
  title = {A Spelling Correction Model for End-to-End Speech Recognition},
  booktitle = icassp,
  year = {2019},
  pdf = {https://arxiv.org/abs/1902.07178},
}

@inproceedings{alon2019contextual,
  annote = asr,
  author = {U. Alon and G. Pundak and T. N. Sainath},
  title = {Contextual Speech Recognition with Difficult Negative Training Examples},
  booktitle = icassp,
  year = {2019},
  pdf = {https://arxiv.org/abs/1810.12170},
}

@inproceedings{qin2019imperceptible,
  annote = asr,
  author = {Y. Qin and N. Carlini and I. Goodfellow and G. Cottrell and C.  Raffel},
  title = {Imperceptible, Robust, and Targeted Adversarial Examples for Automatic Speech Recognition},
  booktitle = icml,
  year = {2019},
  pdf = {https://arxiv.org/abs/1903.10346},
}

@inproceedings{park2019specaugment,
  annote = asr,
  author = {D. S. Park and W. Chan and Y. Zhang and C. Chiu and B. Zoph and E. D. Cubuk and Q. V. Le},
  title = {{SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition}},
  booktitle = {arXiv},
  year = {2019},
  pdf = {https://arxiv.org/abs/1904.08779}
}

@inproceedings{li2019semisupervised,
  annote = asr,
  title = {Semi-supervised Training for End-to-end Models via Weak Distillation},
  author = {B. Li and T. N. Sainath and R. Pang and Z. Wu},
  booktitle = icassp,
  year = {2019},
  pdf = {https://ieeexplore.ieee.org/document/8682172},
}

@inproceedings{chang2019joint,
  annote = asr,
  title = {Joint Endpointing and Decoding with End-to-end Models},
  author = {S.-Y. Chang and R. Prabhavalkar and Y. He and T. N. Sainath and G. Simko},
  booktitle = icassp,
  year = {2019},
  pdf = {https://ieeexplore.ieee.org/document/8683109},
}

@inproceedings{heymann2019improving,
  annote = asr,
  title = {Improving CTC Using Stimulated Learning for Sequence Modeling},
  author = {J. Heymann and K. C. Sim and B. Li},
  booktitle = icassp,
  year = {2019},
  pdf = {https://ieeexplore.ieee.org/document/8682700},
}

@inproceedings{bruguier2019phoebe,
  annote = asr,
  title = {Phoebe: Pronunciation-aware Contextualization for End-to-end Speech Recognition},
  author = {A. Bruguier and R. Prabhavalkar and G. Pundak and T. N. Sainath},
  booktitle = icassp,
  year = {2019},
  pdf = {https://ieeexplore.ieee.org/document/8682441},
}

@inproceedings{he2019streaming,
  annote = asr,
  title = {Streaming End-to-end Speech Recognition for Mobile Devices},
  author = {Y. He and T. N. Sainath and R. Prabhavalkar and I. McGraw and R. Alvarez and D. Zhao and D. Rybach and A. Kannan and Y. Wu and R. Pang and Q. Liang and D. Bhatia and Y. Shangguan and B. Li and G. Pundak and K. C. Sim and T. Bagby and S.-Y. Chang and K. Rao and A. Gruenstein},
  booktitle = icassp,
  year = {2019},
  pdf = {https://arxiv.org/abs/1811.06621},
}

@inproceedings{irie2019unit,
  annote = asr,
  author = {K. Irie and R. Prabhavalkar and A. Kannan and A. Bruguier and D. Rybach and P. Nguyen},
  title = {On the Choice of Modeling Unit for Sequence-to-Sequence Speech Recognition},
  booktitle = interspeech,
  year = {2019},
  pdf = {https://arxiv.org/abs/1902.01955},
}

@inproceedings{peyser2019numerics,
  annote = asr,
  title = {{Improving Performance of End-to-End ASR on Numeric Sequences}},
  author = {C. Peyser and H. Zhang and T. N. Sainath and Z. Wu},
  booktitle = interspeech,
  year = {2019},
  pdf = {https://arxiv.org/abs/1907.01372},
}

@inproceedings{zhao2019shallow,
  annote = asr,
  author = {D. Zhao and T. N. Sainath and D. Rybach and D. Bhatia and B. Li and R. Pang},
  title = {Shallow-Fusion End-to-End Contextual Biasing},
  booktitle = interspeech,
  year = {2019},
  pdf = {https://www.isca-speech.org/archive/Interspeech_2019/pdfs/1209.pdf},
}

@inproceedings{TaraRuoming19,
  annote = asr,
  title={Two-Pass End-to-End Speech Recognition},
  author={T. N. Sainath and R. Pang and D. Rybach and Y. He and R. Prabhavalkar and W. Li and M. Visontai and Q. Liang and T. Strohman and Y. Wu and I. McGraw and C.-C. Chiu},
  booktitle=interspeech,
  year={2019},
  pdf = {https://arxiv.org/abs/1908.10992},
}

@inproceedings{Chiu19longform,
  annote = asr,
  title={A Comparison of End-to-end Models for Long-form Speech Recognition},
  author={C.-C. Chiu and W. Han and Y. Zhang and R. Pang and S. Kishchenko and P. Nguyen and A. Narayanan and H. Liao and S. Zhang and A. Kannan and R. Prabhavalkar and Z. Chen and T. Sainath and Y. Wu},
  booktitle = asru,
  year={2019},
  pdf = {https://arxiv.org/abs/1911.02242}
}

@inproceedings{narayanan2019longform,
  annote = asr,
  author={A. Narayanan and R. Prabhavalkar and C.C. Chiu and D. Rybach and T.N. Sainath and T. Strohman},
  title={Recognizing Long-Form Speech Using Streaming End-to-End Models},
  booktitle = asru,
  year={2019},
  pdf = {https://arxiv.org/abs/1910.11455}
}

@inproceedings{sainath2020,
  annote = asr,
  title = {An Attention-Based Joint Acoustic and Text On-Device End-to-End Model},
  author = {Tara N. Sainath and Ruoming Pang and Ron Weiss and Yanzhang He and Chung-Cheng Chiu and Trevor Strohman},
  booktitle = icassp,
  year = {2020},
}

@inproceedings{lu2020,
  annote = asr,
  title = {Speech Sentiment Analysis via Pre-Trained Features from End-To-End ASR Models},
  author = {Zhiyun Lu and Liangliang Cao and Yu Zhang and Chung-Cheng Chiu and James Fan},
  booktitle = icassp,
  year = {2020},
}

@inproceedings{park2020,
  annote = asr,
  title = {SpecAugment on Large Scale Datasets},
  author = {Daniel Park and Yu Zhang and Chung-Cheng Chiu and Youzheng Chen and Bo Li and William Chan and Quoc Le and Yonghui Wu},
  booktitle = icassp,
  year = {2020},
  pdf = {https://arxiv.org/abs/1912.05533}
}

@inproceedings{e2e2020,
  annote = asr,
  title = {A Streaming On-Device End-to-End Model Surpassing Server-Side Conventional Model Quality and Latency},
  author = {Tara Sainath and Yanzhang He and Bo Li and Arun Narayanan and Ruoming Pang and Antoine Bruguier and Shuo-yiin Chang and Wei Li and Raziel Alvarez and Zhifeng Chen and Chung-cheng Chiu and David Garcia and Alex Gruenstein and Ke Hu and Minho Jin and Anjuli Kannan and Qiao Liang and Ian McGraw and Cal Peyser and Rohit Prabhavalkar and Golan Pundak and David Rybach and Yuan Shangguan and Yash Sheth and Trevor Strohman and Mirko Visontai and Yonghui Wu and Yu Zhang and Ding Zhao},
  booktitle = icassp,
  year = {2020},
}

@inproceedings{conformer2020,
  annote = asr,
  title={Conformer: Convolution-augmented Transformer for Speech Recognition},
  author={Anmol Gulati and James Qin and Chung-Cheng Chiu and Niki Parmar and Yu Zhang and Jiahui Yu and Wei Han and Shibo Wang and Zhengdong Zhang and Yonghui Wu and Ruoming Pang},
  booktitle=interspeech,
  year={2020},
  pdf = {https://arxiv.org/abs/2005.08100},
}

@inproceedings{contextnet2020,
  annote = asr,
  title={ContextNet: Improving Convolutional Neural Networks for Automatic Speech Recognition with Global Context},
  author={Wei Han and Zhengdong Zhang and Yu Zhang and Jiahui Yu and Chung-Cheng Chiu and James Qin and Anmol Gulati and Ruoming Pang and Yonghui Wu},
  booktitle=interspeech,
  year={2020},
  pdf = {https://arxiv.org/abs/2005.03191},
}

@inproceedings{rescore2020,
  annote = asr,
  title={Parallel Rescoring with Transformer for Streaming On-Device Speech Recognition},
  author={Wei Li and James Qin and Chung-Cheng Chiu and Ruoming Pang and Yanzhang He},
  booktitle=interspeech,
  year={2020}
}

@inproceedings{noisystudent2020,
  annote = asr,
  title={Improved Noisy Student Training for Automatic Speech Recognition},
  author={Daniel S. Park and Yu Zhang and Ye Jia and Wei Han and Chung-Cheng Chiu and Bo Li and Yonghui Wu and Quoc V. Le},
  booktitle=interspeech,
  year={2020},
  pdf = {https://arxiv.org/abs/2005.09629}
}


@inproceedings{sas2020,
  annote = asr,
  author = {Yu Zhang and James Qin and Daniel S. Park and Wei Han and Chung-Cheng Chiu and Ruoming Pang and Quoc V. Le and Yonghui Wu},
  title = {Pushing the Limits of Semi-Supervised Learning for Automatic Speech Recognition},
  booktitle = {NeurIPS 2020 Workshop on Self-Supervised Learning for Speech and Audio Processing},
  year = {2020},
  pdf = {https://arxiv.org/abs/2010.10504},
}


@inproceedings{longform2020,
  annote = asr,
  author = {Chung-Cheng Chiu and Arun Narayanan and Wei Han and Rohit Prabhavalkar and Yu Zhang and Navdeep Jaitly and Ruoming Pang and Tara N. Sainath and Patrick Nguyen and Liangliang Cao and Yonghui Wu},
  title = {RNN-T Models Fail to Generalize to Out-of-Domain Audio: Causes and Solutions},
  booktitle = slt,
  year = {2020},
  pdf = {https://arxiv.org/abs/2005.03271},
}

@inproceedings{panchapagesan2021,
  annote = asr,
  title = {Efficient Knowledge Distillation for RNN-Transducer Models},
  author = {Sankaran Panchapagesan and Daniel S. Park and Chung-Cheng Chiu and Yuan Shangguan and Qiao Liang and Alexander Gruenstein},
  booktitle = icassp,
  year = {2021},
  pdf = {https://arxiv.org/abs/2011.06110}
}

@inproceedings{cascaded2021,
  annote = asr,
  title = {Cascaded encoders for unifying streaming and non-streaming ASR},
  author = {Arun Narayanan and Tara N. Sainath and Ruoming Pang and Jiahui Yu and Chung-Cheng Chiu and Rohit Prabhavalkar and Ehsan Variani and Trevor Strohman},
  booktitle = icassp,
  year = {2021},
  pdf = {https://arxiv.org/abs/2010.14606}
}

@inproceedings{betterfaster2021,
  annote = asr,
  title = {A Better and Faster End-to-End Model for Streaming ASR},
  author = {Bo Li and Anmol Gulati and Jiahui Yu and Tara N. Sainath and Chung-Cheng Chiu and Arun Narayanan and Shuo-Yiin Chang and Ruoming Pang and Yanzhang He and James Qin and Wei Han and Qiao Liang and Yu Zhang and Trevor Strohman and Yonghui Wu},
  booktitle = icassp,
  year = {2021},
  pdf = {https://arxiv.org/abs/2011.10798}
}

@inproceedings{doutre2021,
  annote = asr,
  title = {Improving Streaming Automatic Speech Recognition With Non-Streaming Model Distillation On Unsupervised Data},
  author = {Thibault Doutre and Wei Han and Min Ma and Zhiyun Lu and Chung-Cheng Chiu and Ruoming Pang and Arun Narayanan and Ananya Misra and Yu Zhang and Liangliang Cao},
  booktitle = icassp,
  year = {2021},
  pdf = {https://arxiv.org/abs/2010.12096}
}
@inproceedings{doutre2021b,
  annote = asr,
  title = {Bridging the gap between streaming and non-streaming {ASR} systems bydistilling ensembles of {CTC} and {RNN-T} models},
  author = {Thibault Doutre and Wei Han and Chung-Cheng Chiu and Ruoming Pang and Olivier Siohan and Liangliang Cao},
  booktitle = interspeech,
  year = {2021},
  pdf = {https://arxiv.org/abs/2104.14346}
}

@inproceedings{fastemit2021,
  annote = asr,
  title = {FastEmit: Low-latency Streaming ASR with Sequence-level Emission Regularization},
  author = {Jiahui Yu and Chung-Cheng Chiu and Bo Li and Shuo-yiin Chang and Tara N. Sainath and Yanzhang He and Arun Narayanan and Wei Han and Anmol Gulati and Yonghui Wu and Ruoming Pang},
  booktitle = icassp,
  year = {2021},
  pdf = {https://arxiv.org/abs/2010.11148}
}

@inproceedings{lu2021,
  annote = asr,
  title = {Exploring Targeted Universal Adversarial Perturbations to End-to-end ASR Models},
  author = {Zhiyun Lu and Wei Han and Yu Zhang and Liangliang Cao},
  booktitle = interspeech,
  year = {2021},
  pdf = {https://arxiv.org/abs/2104.02757}
}

@inproceedings{li2021rebm,
  annote = asr,
  title = {Residual Energy-Based Models for End-to-End Speech Recognition},
  author = {Qiujia Li and Yu Zhang and Bo Li and Liangliang Cao and Philip C. Woodland},
  booktitle = interspeech,
  year = {2021},
  pdf = {https://arxiv.org/abs/2103.14152}
}

@inproceedings{li2021cem,
  annote = asr,
  title = {Confidence Estimation for Attention-based Sequence-to-sequence Models for Speech Recognition},
  author = {Qiujia Li and David Qiu and Yu Zhang and Bo Li and Yanzhang He and Philip C. Woodland and Liangliang Cao and Trevor Strohman},
  booktitle = icassp,
  year = {2021},
  pdf = {https://arxiv.org/abs/2010.11428}
}
%%%%%%%%%%%%%%%%%%%%
% Language understanding papers.

@inproceedings{kannan2018semi,
  annote = nlu,
  author = {A. Kannan and K. Chen and D. Jaunzeikare and A. Rajkomar},
  title = {{Semi-Supervised Learning for Information Extraction from Dialogue}},
  booktitle = interspeech,
  year = {2018},
  pdf = {https://www.isca-speech.org/archive/Interspeech_2018/pdfs/1318.pdf},
}

@inproceedings{yavuz2018calcs,
  annote = nlu,
  author = {S. Yavuz and C. C. Chiu and P. Nguyen and Y. Wu},
  title = {{CaLcs: Continuously Approximating Longest Common Subsequence for Sequence Level Optimization}},
  booktitle = emnlp,
  year = {2018},
  pdf = {http://aclweb.org/anthology/D18-1406},
}

@inproceedings{haghani2018s2p,
  annote = nlu,
  author = {P. Haghani and A. Narayanan and M. Bacchiani and G. Chuang and N. Gaur and P. Moreno and R. Prabhavalkar and Z. Qu and A. Waters},
  title = {{From Audio to Semantics: Approaches to End-to-End Spoken Language Understanding}},
  booktitle = slt,
  year = {2018},
  pdf = {https://arxiv.org/abs/1809.09190},
}

@inproceedings{chen2019smartcompose,
  annote = nlu,
  author = {M. X. Chen and B. N. Lee and G. Bansal and Y. Cao and S. Zhang and J. Lu and J. Tsay and Y. Wang and A. M. Dai and Z. Chen and T. Sohn and Y. Wu},
  title = {Gmail Smart Compose: Real-Time Assisted Writing},
  booktitle = {Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining},
  year = {2019},
  publisher = {Association for Computing Machinery},
  url = {https://dl.acm.org/doi/10.1145/3292500.3330723},
  pdf = {https://arxiv.org/abs/1906.00080},
}


%%%%%%%%%%%%%%%%%%%%
% Speech synthesis papers.

@inproceedings{shen2018natural,
  annote = tts,
  title = {Natural {TTS} Synthesis by Conditioning {WaveNet} on Mel Spectrogram Predictions},
  author =  {J. Shen and R. Pang and  R. J. Weiss and M. Schuster and N. Jaitly and Z. Yang and Z. Chen and Y. Zhang and Y. Wang and R.J. Skerry-Ryan and R. A. Saurous and Y. Agiomyrgiannakis and Y. Wu},
  booktitle = icassp,
  year = {2018},
  pdf = {https://arxiv.org/abs/1712.05884},
  sound_examples = {https://google.github.io/tacotron/publications/tacotron2/index.html},
}

@inproceedings{chorowski2018styletransfer,
  annote = tts,
  title = {On Using Backpropagation for Speech Texture Generation and Voice Conversion},
  author = {J. Chorowski and R. J. Weiss and R. A. Saurous and S. Bengio},
  booktitle = icassp,
  year = {2018},
  pdf = {https://arxiv.org/abs/1712.08363},
  sound_examples = {https://google.github.io/speech_style_transfer/samples.html},
}

@inproceedings{jia2018multispeaker,
  annote = tts,
  title = {Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis},
  author = {Y. Jia and Y. Zhang and R. J. Weiss and Q. Wang and J. Shen and F. Ren and Z. Chen and P. Nguyen and R. Pang and I. Lopez-Moreno and Y. Wu},
  booktitle = nips,
  year = {2018},
  pdf = {https://arxiv.org/abs/1806.04558},
  sound_examples = {https://google.github.io/tacotron/publications/speaker_adaptation/index.html},
}

@inproceedings{hsu2019hierarchical,
  annote = tts,
  title = {Hierarchical Generative Modeling for Controllable Speech Synthesis},
  author = {W. N. Hsu and Y. Zhang and R. J. Weiss and H. Zen and Y. Wu and Y. Wang and Y. Cao and Y. Jia and Z. Chen and J. Shen and P. Nguyen and R. Pang},
  booktitle = iclr,
  year = {2019},
  pdf = {https://arxiv.org/abs/1810.07217},
  sound_examples = {https://google.github.io/tacotron/publications/gmvae_controllable_tts/index.html},
}

@inproceedings{hsu2018disentangling,
  annote = tts,
  author = {W. N. Hsu and Y. Zhang and R. J. Weiss and Y. A. Chung and Y. Wang and Y. Wu and J. Glass},
  title = {Disentangling Correlated Speaker and Noise for Speech Synthesis via Data Augmentation and Adversarial Factorization},
  booktitle = {NeurIPS 2018 Workshop on Interpretability and Robustness in Audio, Speech, and Language},
  year = {2018},
  pdf = {https://openreview.net/forum?id=Bkg9ZeBB37},
}

@inproceedings{zen2019libritts,
  annote = tts,
  title = {{LibriTTS}: A Corpus Derived from {LibriSpeech} for Text-to-Speech},
  author =  {H. Zen and V. Dang and R. Clark and Y. Zhang and R. J. Weiss and Y. Jia and Z. Chen and Y. Wu},
  booktitle = interspeech,
  year = {2019},
  pdf = {https://arxiv.org/abs/1904.02882},
  data = {http://www.openslr.org/60},
}

@inproceedings{biadsy2019parrotron,
  annote = tts,
  author = {F. Biadsy and R. J. Weiss and P. Moreno and D. Kanvesky and Y. Jia},
  title = {Parrotron: An End-to-End Speech-to-Speech Conversion Model and its Applications to Hearing-Impaired Speech and Speech Separation},
  booktitle = interspeech,
  year = {2019},
  pdf = {https://arxiv.org/abs/1904.04169},
  sound_examples = {https://google.github.io/tacotron/publications/parrotron},
}

@inproceedings{zhang2019learning,
  annote = tts,
  author = {Y. Zhang and R. J. Weiss and H. Zen and Y. Wu and Z. Chen and R. J. Skerry-Ryan and Y. Jia and A. Rosenberg and B. Ramabhadran},
  title = {Learning to Speak Fluently in a Foreign Language: Multilingual Speech Synthesis and Cross-Language Voice Cloning},
  booktitle = interspeech,
  year = {2019},
  pdf = {https://arxiv.org/abs/1907.04448},
  sound_examples = {http://google.github.io/tacotron/publications/multilingual},
}

@inproceedings{sun2020finegrained,
  annote = tts,
  author = {G. Sun and Y. Zhang and R. J. Weiss and Y. Cao and H. Zen and Y. Wu},
  title = {Fully-hierarchical Fine-grained Prosody Modeling for Interpretable Speech Synthesis},
  booktitle = icassp,
  year = {2020},
  pdf = {https://arxiv.org/abs/2002.03785},
  sound_examples = {https://google.github.io/tacotron/publications/hierarchical_prosody},
}

@inproceedings{sun2020prosodyprior,
  annote = tts,
  author = {G. Sun and Y. Zhang and R. J. Weiss and Y. Cao and H. Zen and A. Rosenberg and B. Ramabhadran and Y. Wu},
  title = {Generating Diverse and Natural Text-to-Speech Samples Using A Quantized Fine-grained {VAE} and Auto-regressive Prosody Prior},
  booktitle = icassp,
  year = {2020},
  pdf = {https://arxiv.org/abs/2002.03788},
  sound_examples = {https://google.github.io/tacotron/publications/prosody_prior},
}

@article{shen2020non,
  annote = tts,
  title={Non-attentive Tacotron: Robust and controllable neural TTS synthesis including unsupervised duration modeling},
  author={Shen, Jonathan and Jia, Ye and Chrzanowski, Mike and Zhang, Yu and Elias, Isaac and Zen, Heiga and Wu, Yonghui},
  journal={arXiv preprint arXiv:2010.04301},
  year={2020},
  pdf = {https://arxiv.org/abs/2010.04301},
  sound_examples = {https://google.github.io/tacotron/publications/nat},
}

@inproceedings{chen2020wavegrad,
  annote = tts,
  title={WaveGrad: Estimating gradients for waveform generation},
  author={Chen, Nanxin and Zhang, Yu and Zen, Heiga and Weiss, Ron J and Norouzi, Mohammad and Chan, William},
  booktitle=iclr,
  year={2020},
  pdf = {https://arxiv.org/abs/2009.00713},
  sound_examples = {https://wavegrad.github.io},
}

@inproceedings{chen2021wavegrad2,
  annote = tts,
  title={WaveGrad 2: Iterative Refinement for Text-to-Speech Synthesis},
  author={Chen, Nanxin and Zhang, Yu and Zen, Heiga and Weiss, Ron J and Norouzi, Mohammad and Dehak, Najim and Chan, William},
  booktitle=interspeech,
  year={2021},
  pdf = {https://arxiv.org/abs/2106.09660},
  sound_examples = {https://wavegrad.github.io/v2},
}

@inproceedings{elias2021parallel,
  annote = tts,
  title={Parallel Tacotron: Non-autoregressive and controllable TTS},
  author={Elias, Isaac and Zen, Heiga and Shen, Jonathan and Zhang, Yu and Jia, Ye and Weiss, Ron J and Wu, Yonghui},
  booktitle=icassp,
  pages={5709--5713},
  year={2021},
  organization={IEEE},
  pdf = {https://arxiv.org/abs/2010.11439},
  sound_examples = {https://google.github.io/tacotron/publications/parallel_tacotron},
}

@inproceedings{elias2021parallel2,
  annote = tts,
  title={Parallel Tacotron 2: A Non-Autoregressive Neural TTS Model with Differentiable Duration Modeling},
  author={Elias, Isaac and Zen, Heiga and Shen, Jonathan and Zhang, Yu and Jia, Ye and Skerry-Ryan, RJ and Wu, Yonghui},
  booktitle=interspeech,
  year={2021},
  pdf = {https://arxiv.org/abs/2103.14574},
  sound_examples = {https://google.github.io/tacotron/publications/parallel_tacotron_2},
}

@inproceedings{jia2021png,
  annote = tts,
  title={PnG BERT: Augmented BERT on Phonemes and Graphemes for Neural TTS},
  author={Jia, Ye and Zen, Heiga and Shen, Jonathan and Zhang, Yu and Wu, Yonghui},
  booktitle=interspeech,
  year={2021},
  pdf = {https://arxiv.org/abs/2103.15060},
  sound_examples = {https://google.github.io/tacotron/publications/png_bert},
}

%%%%%%%%%%%%%%%%%%%%
% Speech-to-text translation papers.

@inproceedings{weiss2017sequence,
  annote = st,
  title = {Sequence-to-Sequence Models Can Directly Translate Foreign Speech},
  author = {R. J. Weiss and J. Chorowski and N. Jaitly and Y. Wu and Z. Chen},
  booktitle = interspeech,
  year = {2017},
  pdf = {https://arxiv.org/abs/1703.08581},
}

@inproceedings{jia2019leveraging,
  annote = st,
  author = {Y. Jia and M. Johnson and W. Macherey and R. J. Weiss and Y. Cao and C. C. Chiu and N. Ari and S. Laurenzo and Y. Wu},
  title = {Leveraging Weakly Supervised Data to Improve End-to-End Speech-to-Text Translation},
  booktitle = icassp,
  year = {2019},
  pdf = {https://arxiv.org/abs/1811.02050},
}

@inproceedings{jia2019direct,
  annote = st,
  author = {Y. Jia and R. J. Weiss and F. Biadsy and W. Macherey and M. Johnson and Z. Chen and Y. Wu},
  title = {Direct speech-to-speech translation with a sequence-to-sequence model},
  booktitle = interspeech,
  year = {2019},
  pdf = {https://arxiv.org/abs/1904.06037},
  sound_examples = {https://google-research.github.io/lingvo-lab/translatotron},
}

@article{jia2021translatotron,
  annote = st,
  title={Translatotron 2: Robust direct speech-to-speech translation},
  author={Jia, Ye and Ramanovich, Michelle Tadmor and Remez, Tal and Pomerantz, Roi},
  journal={arXiv preprint arXiv:2107.08661},
  year={2021},
  pdf = {https://arxiv.org/abs/2107.08661},
  sound_examples = {https://google-research.github.io/lingvo-lab/translatotron2},
}

%%%%%%%%%%%%%%%%%%%%
% Speech enhancement papers.

@inproceedings{ding2021textual,
  annote = enhancement,
  title={Textual Echo Cancellation},
  author={Ding, Shaojin and Jia, Ye and Hu, Ke and Wang, Quan},
  booktitle = asru,
  year = {2021},
  pdf = {https://arxiv.org/abs/2008.06006},
  sound_examples = {https://google.github.io/speaker-id/publications/TEC/},
}

@inproceedings{narayanan2021cross,
  annote = enhancement,
  title={Cross-Attention Conformer for Context Modeling in Speech Enhancement for ASR},
  author={Arun Narayanan and  Chung-Cheng Chiu and Tom O'Malley and Quan Wang and Yanzhang He},
  booktitle = asru,
  year = {2021},
  pdf = {https://arxiv.org/abs/2111.00127},
}

@inproceedings{omalley2021aconformer,
  annote = enhancement,
  title={A Conformer-Based ASR Frontend For Joint Acoustic Echo Cancellation, Speech Enhancement and Speech Separation},
  author={Tom O'Malley and Arun Narayanan and Quan Wang and Alex Park and James Walker and Nathan Howard},
  booktitle = asru,
  year = {2021},
  pdf = {https://arxiv.org/abs/2111.09935},
}

%%%%%%%%%%%%%%%%%%%%
% Speaker and language recognition papers.

@inproceedings{wang2022attentive,
  annote = slr,
  title={Attentive Temporal Pooling for Conformer-based Streaming Language Identification in Long-form Speech},
  author={Quan Wang and Yang Yu and Jason Pelecanos and Yiling Huang and Ignacio Lopez Moreno},
  year = {2022},
  pdf = {https://arxiv.org/abs/2202.12163},
}

@inproceedings{pelecanos2022parameter,
  annote = slr,
  title={Parameter-Free Attentive Scoring for Speaker Verification},
  author={Jason Pelecanos and Quan Wang and Yiling Huang and Ignacio Lopez Moreno},
  year = {2022},
  pdf = {https://arxiv.org/abs/2203.05642},
  code = {https://github.com/google/speaker-id/tree/master/attentive_scoring},
}

@inproceedings{xia2022turn,
  annote = slr,
  title={{Turn-to-Diarize}: Online Speaker Diarization Constrained by Transformer Transducer Speaker Turn Detection},
  author={Wei Xia and Han Lu and Quan Wang and Anshuman Tripathi and Yiling Huang and Ignacio Lopez Moreno and Hasim Sak},
  booktitle=icassp,
  year={2022},
  pdf = {https://arxiv.org/abs/2109.11641},
  code = {https://github.com/wq2012/SpectralCluster},
}

%%%%%%%%%%%%%%%%%%%%
% Optimization papers.

@article{anil2020second,
  annote = opt,
  title={Second Order Optimization Made Practical},
  author={Anil, Rohan and Gupta, Vineet and Koren, Tomer and Regan, Kevin and Singer, Yoram},
  journal={arXiv preprint arXiv:2002.09018},
  pdf = {https://arxiv.org/abs/2002.09018},
  year={2020}
}

@article{agarwal2020disentangling,
  annote = opt,
  title={Disentangling Adaptive Gradient Methods from Learning Rates},
  author={Agarwal, Naman and Anil, Rohan and Hazan, Elad and Koren, Tomer and Zhang, Cyril},
  journal={arXiv preprint arXiv:2002.11803},
  pdf = {https://arxiv.org/abs/2002.11803},
  year={2020}
}

@inproceedings{anil2019memory,
  annote = opt,
  title={Memory Efficient Adaptive Optimization},
  author={Anil, Rohan and Gupta, Vineet and Koren, Tomer and Singer, Yoram},
  booktitle={Advances in Neural Information Processing Systems},
  pdf = {https://arxiv.org/abs/1901.11150},
  pages={9749--9758},
  year={2019}
}