Parallel Rescoring with Transformer for Streaming On-Device Speech Recognition

Wei Li
Wei Li
James Qin
James Qin
Yanzhang He
Yanzhang He

INTERSPEECH, pp. 2122-2126, 2020.

Cited by: 5|Views39
EI

Abstract:

Recent advances of end-to-end models have outperformed conventional models through employing a two-pass model. The two-pass model provides better speed-quality trade-offs for on-device speech recognition, where a 1st-pass model generates hypotheses in a streaming fashion, and a 2nd-pass model re-scores the hypotheses with full audio seq...More

Code:

Data:

Your rating :
0

 

Tags
Comments