Xiaohui Zhang

RESEARCH SCIENTIST | NEW YORK CITY, UNITED STATES

Xiaohui is a Research Scientist and one of the founding members of the Video Speech Recognition team at Facebook AI Applied Research. Xiaohui received an M.S.E. in Applied Mathematics and Statistics and a Ph.D. from the Center for Language and Speech Processing at the Johns Hopkins University. Xiaohui's areas of interest include acoustic modeling, pronunciation learning and OOV recovery for ASR, 2nd order optimization methods for deep learning, and actively contributed to the open-source ASR toolkit Kaldi.

Xiaohui's Publications

November 04, 2020

RESEARCH

NLP

OOV Recovery with Efficient 2nd Pass Decoding and Open-vocabulary Word-level RNNLM Rescoring for Hybrid ASR

Xiaohui Zhang, Daniel Povey, Sanjeev Khudanpur

November 04, 2020

April 30, 2020

RESEARCH

NLP

Transformer-based Acoustic Modeling for Hybrid Speech Recognition

Yongqiang Wang, Abdelrahman Mohamed, Alex Xiao, Andros Tjandra, Christian Fuegen, Chunxi Liu, Duc Le, Frank Zhang, Geoffrey Zweig, Hongzhao Huang, Jay Mahadeokar, Mike Seltzer, Xiaohui Zhang

April 30, 2020