Towards Fast and Accurate Streaming End-to-End ASR

Chang Shuo-yiin
Chang Shuo-yiin
He Yanzhang
He Yanzhang
Strohman Trevor
Strohman Trevor

ICASSP, pp. 6069-6073, 2020.

Cited by: 2|Bibtex|Views64|Links
EI

Abstract:

End-to-end (E2E) models fold the acoustic, pronunciation and language models of a conventional speech recognition model into one neural network with a much smaller number of parameters than a conventional ASR system, thus making it suitable for on-device applications. For example, recurrent neural network transducer (RNN-T) as a streami...More

Code:

Data:

Your rating :
0

 

Tags
Comments