Thibault Doutre
发表
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).
Input Length Matters: An Empirical Study Of RNN-T And MWER Training For Long-form Telephony Speech Recognition
pdf
Rohit Prabhavalkar,
Trevor Strohman,
Thibault Doutre,
2021,
ArXiv.
Rohit Prabhavalkar,
Liangliang Cao,
Trevor Strohman,
2021,
2110.03841.