201125 Streaming end-to-end multi-talker speech recognition.md

https://arxiv.org/abs/2011.13148

Streaming end-to-end multi-talker speech recognition (Liang Lu, Naoyuki Kanda, Jinyu Li, Yifan Gong)

역시나 rnn-t 기반. efficient rnn-t 구현이 필요하다...!

#transducer #asr