Improving RNN Transducer Based ASR with Auxiliary Tasks

Chunxi Liu
Chunxi Liu
Frank Zhang
Frank Zhang
Duc Le
Duc Le
Suyoun Kim
Suyoun Kim
Yatharth Saraf
Yatharth Saraf
Cited by: 0|Bibtex|Views12
Other Links: arxiv.org

Abstract:

End-to-end automatic speech recognition (ASR) models with a single neural network have recently demonstrated state-of-the-art results compared to conventional hybrid speech recognizers. Specifically, recurrent neural network transducer (RNN-T) has shown competitive ASR performance on various benchmarks. In this work, we examine ways in ...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments