Multi-Speaker ASR Combining Non-Autoregressive Conformer CTC and Conditional Speaker Chain.

Pengcheng Guo Xuankai Chang Shinji Watanabe Lei Xie

Published in: CoRR (2021)

Keyphrases

autoregressive
automatic speech recognition
speech recognition
non stationary
moving average
gaussian markov random field
random field models
hidden markov models
random fields
speech signal
feature extraction
conditional random fields
noisy environments