Improving Streaming Automatic Speech Recognition With Non-Streaming Model Distillation On Unsupervised Data

Cited by: 1|Views30

Abstract:

Streaming end-to-end automatic speech recognition (ASR) models are widely used on smart speakers and on-device applications. Since these models are expected to transcribe speech with minimal latency, they are constrained to be causal with no future context, compared to their non-streaming counterparts. Consequently, streaming models usu...More

Code:

Data:

Full Text
Bibtex
Your rating :
0

 

Tags
Comments