Patrick Nguyen

Google (United States) — United States

Computer Science · Physical Sciences

24h-index14.8kcitations79works0.02yr avg
OpenAlex↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Speech Recognition and Synthesis(60), Music and Audio Processing(41), Speech and Audio Processing(34), Natural Language Processing Techniques(32), Topic Modeling(23)

Publications79 total

RNN-T Models Fail to Generalize to Out-of-Domain Audio: Causes and Solutions
2021· 24 cited
RNN-T Models Fail to Generalize to Out-of-Domain Audio: Causes and Solutions
arXiv (Cornell University)·2020· 12 citedOpen Access
A comparison of end-to-end models for long-form speech recognition
arXiv (Cornell University)·2019· 13 citedOpen Access
On the Choice of Modeling Unit for Sequence-to-Sequence Speech Recognition
2019· 40 citedOpen Access
Lingvo: a Modular and Scalable Framework for Sequence-to-Sequence Modeling
arXiv (Cornell University)·2019· 183 citedOpen Access
Model Unit Exploration for Sequence-to-Sequence Speech Recognition.
arXiv (Cornell University)·2019· 14 citedOpen Access
A Comparison of End-to-End Models for Long-Form Speech Recognition
IEEE Conference Proceedings·2019
Hierarchical Generative Modeling for Controllable Speech Synthesis
arXiv (Cornell University)·2018· 45 citedOpen Access
Speech Recognition for Medical Conversations
2018· 69 cited
Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis
arXiv (Cornell University)·2018· 433 citedOpen Access
Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis
Neural Information Processing Systems·2018· 229 cited
An Analysis of Incorporating an External Language Model into a Sequence-to-Sequence Model
2018· 11 citedOpen Access
No Need for a Lexicon? Evaluating the Value of the Pronunciation Lexica in End-to-End Models
2018Open Access
Minimum Word Error Rate Training for Attention-Based Sequence-to-Sequence Models
2018· 5 citedOpen Access
Improving the Performance of Online Neural Transducer Models
2018· 56 cited
State-of-the-Art Speech Recognition with Sequence-to-Sequence Models
2018· 82 citedOpen Access
Multi-Dialect Speech Recognition with a Single Sequence-to-Sequence Model
2018· 115 cited
シーケンス-シーケンスモデルによる最先端音声認識【JST・京大機械翻訳】
IEEE Conference Proceedings·2018
CaLcs: Continuously Approximating Longest Common Subsequence for Sequence Level Optimization
2018· 5 citedOpen Access
Multi-Dialect Speech Recognition With A Single Sequence-To-Sequence Model
arXiv (Cornell University)·2017· 10 citedOpen Access
page 1 of 4Next →

Frequent Co-authors

Yonghui Wu(14), Tara N. Sainath(13), Geoffrey Zweig(13), Navdeep Jaitly(11), Anjuli Kannan(10), Rohit Prabhavalkar(10), Chung‐Cheng Chiu(9), Zhifeng Chen(8), Ruoming Pang(7), Vincent Vanhoucke(6), Jean-Claude Junqua(6), Dong Yu(5), Andrew Senior(5), Ron J. Weiss(5), Jia Ye(4), Jonathan Shen(4), Kanishka Rao(4), Michiel Bacchiani(4), Milind Mahajan(4), Alex Acero(4)