Hank Liao
Hank Liao is a researcher in the speech recognition group with interests in acoustic modeling and large vocabulary speech recognition.
Hank Liao obtained a BASc in Systems Design Engineering from the University of Waterloo in 1999. In 2002 he completed an MPhil from the University of Cambridge. In 2007 he submitted his dissertation on "Uncertainty Decoding for Noise Robust Speech Recognition" to the Cambridge University Engineering Department, supervised by Dr. Mark Gales, and sponsored by Toshiba Research Europe. He has published research on and deployed automatic captioning of YouTube videos, Google Voice's voicemail transcription, and Voice Search speech recognition systems.
Authored Publications
Sort By
Google
USM-SCD: USM-Based Multilingual Speaker Change Detection
Yongqiang Wang
Jason Pelecanos
Yu Zhang
Yiling Huang
Han Lu
ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 11801-11805
On Robustness to Missing Video For Audiovisual Speech Recognition
Dmitriy (Dima) Serdyuk
Olivier Siohan
Transactions on Machine Learning Research (2022)
RECURRENT NEURAL NETWORK TRANSDUCER FOR AUDIO-VISUAL SPEECH RECOGNITION
Basi Garcia
Brendan Shillingford
Olivier Siohan
Yannis Assael
Proceedings of IEEE Automatic Speech Recognition and Understanding Workshop (2019)
Lattice Rescoring Strategies for Long Short Term Memory Language Models in Speech Recognition
Michael Alexander Nirschl
Dan Holtmann-Rice
(2017)
Large Vocabulary Automatic Speech Recognition for Children
Olivier Siohan
Melissa Carroll
Noah Coccaro
Qi-Ming Jiang
Interspeech (2015)
