Minimum latency training of sequence transducers for streaming end-to-end speech recognition.

Yusuke Shinohara Shinji Watanabe 0001 Minimum latency training of sequence transducers for streaming end-to-end speech recognition. 2098-2102 2022 INTERSPEECH https://doi.org/10.21437/Interspeech.2022-10989 conf/interspeech/2022 db/conf/interspeech/interspeech2022.html#Shinohara022