Sequence-to-Sequence Speech Recognition with Time-Depth Separable Convolutions

INTERSPEECH, pp. 3785-3789, 2019.

Cited by: 44|Views68
EI

Abstract:

We propose a fully convolutional sequence-to-sequence encoder architecture with a simple and efficient decoder. Our model improves WER on LibriSpeech while being an order of magnitude more efficient than a strong RNN baseline. Key to our approach is a time-depth separable convolution block which dramatically reduces the number of parame...More

Code:

Data:

Full Text
Bibtex
Your rating :
0

 

Tags
Comments