Yu Zhang

Tara N. Sainath, Ankur Bapna, Khe Chai Sim, 2021, ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

SLAM: A Unified Encoder for Speech and Language Modeling via Speech-Text Joint Pre-Training pdf

Ankur Bapna, Melvin Johnson, Ye Jia, 2021, ArXiv.

Injecting Text in Self-Supervised Speech Pretraining pdf

Bhuvana Ramabhadran, Andrew Rosenberg, Zhehuai Chen, 2021, 2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU).

Cycle-consistency Training for End-to-end Speech Recognition

Jonathan Le Roux, Ramón Fernández Astudillo, Shinji Watanabe, 2018, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speech

Heiga Zen, Yu Zhang, Yonghui Wu, 2019, INTERSPEECH.

Parallel Tacotron 2: A Non-Autoregressive Neural TTS Model with Differentiable Duration Modeling pdf

Heiga Zen, Yonghui Wu, R. J. Skerry-Ryan, 2021, Interspeech.

mSLAM: Massively multilingual joint pre-training for speech and text

Ankur Bapna, Melvin Johnson, Colin Cherry, 2022, ArXiv.

Back-Translation-Style Data Augmentation for end-to-end ASR

Tomoki Toda, Yu Zhang, Ramón Fernández Astudillo, 2018, 2018 IEEE Spoken Language Technology Workshop (SLT).

Learning to Speak Fluently in a Foreign Language: Multilingual Speech Synthesis and Cross-Language Voice Cloning

Heiga Zen, Bhuvana Ramabhadran, Yonghui Wu, 2019, INTERSPEECH.

SpeechStew: Simply Mix All Available Speech Recognition Data to Train One Large Neural Network pdf

Mohammad Norouzi, William Chan, Yu Zhang, 2021, ArXiv.

RNN-T Models Fail to Generalize to Out-of-Domain Audio: Causes and Solutions pdf

Tara N. Sainath, Arun Narayanan, Navdeep Jaitly, 2020, 2021 IEEE Spoken Language Technology Workshop (SLT).

Universal Paralinguistic Speech Representations Using self-Supervised Conformers

A. Jansen, Daniel S. Park, Wei Han, 2021, ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Virtuoso: Massive Multilingual Speech-Text Joint Semi-Supervised Learning for Text-To-Speech

H. Zen, B. Ramabhadran, Ankur Bapna, 2022, ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Bytes Are All You Need: End-to-end Multilingual Speech Recognition and Synthesis with Bytes

Tara N. Sainath, Yu Zhang, William Chan, 2018, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Non-Attentive Tacotron: Robust and Controllable Neural TTS Synthesis Including Unsupervised Duration Modeling pdf

Heiga Zen, Ye Jia, Isaac Elias, 2020, ArXiv.

Improving Streaming Automatic Speech Recognition with Non-Streaming Model Distillation on Unsupervised Data pdf

Arun Narayanan, Liangliang Cao, Yu Zhang, 2020, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

XTREME-S: Evaluating Cross-lingual Speech Representations

Patrick von Platen, Orhan Firat, Michael Auli, 2022, INTERSPEECH.

A Comparison of End-to-End Models for Long-Form Speech Recognition

Tara N. Sainath, Arun Narayanan, Yonghui Wu, 2019, 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU).

Specaugment on Large Scale Datasets

Quoc V. Le, Daniel S. Park, Yu Zhang, 2019, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Speech Recognition with Augmented Synthesized Speech

Bhuvana Ramabhadran, Ye Jia, Yu Zhang, 2019, 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU).

Maestro-U: Leveraging Joint Speech-Text Representation Learning for Zero Supervised Speech ASR

B. Ramabhadran, P. Moreno, Ankur Bapna, 2022, 2022 IEEE Spoken Language Technology Workshop (SLT).

Improving Speech Recognition Using Consistent Predictions on Synthesized Speech

Bhuvana Ramabhadran, Yu Zhang, Pedro J. Moreno, 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Hierarchical Generative Modeling for Controllable Speech Synthesis pdf

Heiga Zen, Yu Zhang, Yuan Cao, 2018, ICLR.

Generating Diverse and Natural Text-to-Speech Samples Using a Quantized Fine-Grained VAE and Autoregressive Prosody Prior

Heiga Zen, Bhuvana Ramabhadran, Yu Zhang, 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Espnet-TTS: Unified, Reproducible, and Integratable Open Source End-to-End Text-to-Speech Toolkit

K. Takeda, T. Toda, Shinji Watanabe, 2019, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Fully-Hierarchical Fine-Grained Prosody Modeling For Interpretable Speech Synthesis

Heiga Zen, Yu Zhang, Ron J. Weiss, 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Disentangling Correlated Speaker and Noise for Speech Synthesis via Data Augmentation and Adversarial Factorization

James Glass, James R. Glass, Yonghui Wu, 2019, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Improving Distortion Robustness of Self-supervised Speech Processing Tasks with Domain Adaptation

Hung-yi Lee, Yu Zhang, Kuan-Po Huang, 2022, Interspeech.

A Streaming On-Device End-To-End Model Surpassing Server-Side Conventional Model Quality and Latency

Tara N. Sainath, Z. Chen, Yonghui Wu, 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Unsupervised Learning of Disentangled Speech Content and Style Representation pdf

Yu Zhang, Ruoming Pang, Andros Tjandra, 2020, Interspeech.

Tts4pretrain 2.0: Advancing the use of Text and Speech in ASR Pretraining with Consistency and Contrastive Losses

B. Ramabhadran, P. Moreno, Yu Zhang, 2022, ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Pushing the Limits of Non-Autoregressive Speech Recognition

Edwin G. Ng, C. Chiu, William Chan, 2021, Interspeech.

A Better and Faster end-to-end Model for Streaming ASR pdf

Tara N. Sainath, Arun Narayanan, Bo Li, 2020, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Improving Confidence Estimation on Out-of-Domain Data for End-to-End Speech Recognition

P. Woodland, Liangliang Cao, Yu Zhang, 2021, ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Multi-Task Learning for End-to-End ASR Word and Utterance Confidence with Deletion Prediction pdf

Ian McGraw, Liangliang Cao, Qiujia Li, 2021, Interspeech.

Residual Energy-Based Models for End-to-End Speech Recognition

P. Woodland, Bo Li, Liangliang Cao, 2021, Interspeech.

Confidence Estimation for Attention-Based Sequence-to-Sequence Models for Speech Recognition pdf

Liangliang Cao, Philip C. Woodland, Yu Zhang, 2020, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Semi-supervised Training for Improving Data Efficiency in End-to-end Speech Synthesis

Yuxuan Wang, Yu Zhang, Yu-An Chung, 2018, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Understanding Shared Speech-Text Representations

Kyle Kastner, B. Ramabhadran, Ankur Bapna, 2023, IEEE International Conference on Acoustics, Speech, and Signal Processing.

Semi-Supervision in ASR: Sequential MixMatch and Factorized TTS-Based Augmentation

H. Zen, B. Ramabhadran, P. Moreno, 2021, Interspeech.

Advances in Joint CTC-Attention Based End-to-End Speech Recognition with a Deep CNN Encoder and RNN-LM

Yu Zhang, Shinji Watanabe, Takaaki Hori, 2017, INTERSPEECH.

Training Text-To-Speech Systems From Synthetic Data: A Practical Approach For Accent Transfer Tasks

Yonghui Wu, H. Zen, V. Wan, 2022, Interspeech.

Miipher: A Robust Speech Restoration Model Integrating Self-Supervised Speech and Text Representations

H. Zen, M. Bacchiani, Ankur Bapna, 2023, ArXiv.

A Large Scale Speech Sentiment Corpus

Liangliang Cao, James Fan, Hao Xu, 2020, LREC.

Speech Sentiment Analysis via Pre-Trained Features from End-to-End ASR Models

C. Chiu, Liangliang Cao, Yu Zhang, 2019, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Modular Hybrid Autoregressive Transducer

B. Ramabhadran, P. Moreno, Rohit Prabhavalkar, 2022, 2022 IEEE Spoken Language Technology Workshop (SLT).

Echo State Speech Recognition

Tara N. Sainath, Yu Zhang, Harsh Shrivastava, 2021, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Exploring Targeted Universal Adversarial Perturbations to End-to-end ASR Models pdf

Liangliang Cao, Wei Han, Yu Zhang, 2021, Interspeech.

Improving Speech Recognition Using GAN-Based Speech Synthesis and Contrastive Unspoken Text Selection

Bhuvana Ramabhadran, Andrew Rosenberg, Pedro J. Moreno, 2020, INTERSPEECH.

Latent Sequence Decompositions pdf

Yu Zhang, Quoc V. Le, Navdeep Jaitly, 2016, ICLR.

AudioPaLM: A Large Language Model That Can Speak and Listen

Tara N. Sainath, Dalia El Badawy, Paul K. Rubenstein, 2023, ArXiv.

Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis

Ron J. Weiss, Z. Chen, Yonghui Wu, 2018, NeurIPS.

LibriTTS-R: A Restored Multi-Speaker Text-to-Speech Corpus

H. Zen, M. Bacchiani, Ankur Bapna, 2023, INTERSPEECH.

Learning Word-Level Confidence for Subword End-To-End ASR

Tara N. Sainath, Ian McGraw, Liangliang Cao, 2021, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Comparison of Soft and Hard Target RNN-T Distillation for Large-Scale ASR

K. Sim, Trevor Strohman, Yu Zhang, 2022, ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Unsupervised Data Selection via Discrete Speech Representation for ASR

Wei Han, Yongqiang Wang, Yu Zhang, 2022, INTERSPEECH.

Efficient Adapters for Giant Speech Models

I. Shafran, Yonghui Wu, H. Soltau, 2023, ArXiv.

Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages

Tara N. Sainath, Yonghui Wu, H. Soltau, 2023, ArXiv.

Miipher: A Robust Speech Restoration Model Integrating Self-Supervised Speech and Text Representations

H. Zen, M. Bacchiani, Ankur Bapna, 2023, 2023 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA).

Training RNNs as Fast as CNNs

Yoav Artzi, Tao Lei, Yu Zhang, 2017, EMNLP 2018.