M3ST: Mix at Three Levels for Speech Translation.

Xuxin Cheng Qianqian Dong Fengpeng Yue Tom Ko Mingxuan Wang Yuexian Zou

Published in: CoRR (2022)

Keyphrases

speech recognition
machine translation
audio visual
high levels
artificial intelligence
cross language information retrieval
speech signal
lower levels
feature extraction
levels of abstraction
endpoint detection