Scaling Up Online Speech Recognition Using ConvNets

Pratap Vineel
Pratap Vineel
Kahn Jacob
Kahn Jacob
Avidov Gilad
Avidov Gilad
Likhomanenko Tatiana
Likhomanenko Tatiana
Liptchinsky Vitaliy
Liptchinsky Vitaliy
Synnaeve Gabriel
Synnaeve Gabriel

INTERSPEECH, pp. 3376-3380, 2020.

Cited by: 11|Views56
EI

Abstract:

We design an online end-to-end speech recognition system based on Time-Depth Separable (TDS) convolutions and Connectionist Temporal Classification (CTC). We improve the core TDS architecture in order to limit the future context and hence reduce latency while maintaining accuracy. The system has almost three times the throughput of a we...More

Code:

Data:

Your rating :
0

 

Tags
Comments