Fast, Simpler and More Accurate Hybrid ASR Systems Using Wordpieces

Zhang Frank
Zhang Frank
Wang Yongqiang
Wang Yongqiang
Zhang Xiaohui
Zhang Xiaohui
Liu Chunxi
Liu Chunxi
Saraf Yatharth
Saraf Yatharth

INTERSPEECH, pp. 976-980, 2020.

Cited by: 0|Bibtex|Views46|DOI:https://doi.org/10.21437/Interspeech.2020-1995
EI
Other Links: arxiv.org|dblp.uni-trier.de|academic.microsoft.com

Abstract:

In this work, we first show that on the widely used LibriSpeech benchmark, our transformer-based context-dependent connectionist temporal classification (CTC) system produces state-of-the-art results. We then show that using wordpieces as modeling units combined with CTC training, we can greatly simplify the engineering pipeline compare...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments