Direct Simultaneous Speech-to-Text Translation Assisted by Synchronized Streaming ASR

To appear in Findings of ACL 2021

Authors: Junkun Chen$^{2}$, Mingbo Ma$^{1}$, Renjie Zheng$^{1}$,Liang Huang$^{12}$

$^1$ Baidu Research, Sunnyvale, CA, USA

$^2$ Oregon State University, Corvallis, OR, USA

 

Example 1:

 

Example 2:

 

Example 3: