ContextNet: Improving Convolutional Neural Networks for Automatic Speech Recognition with Global Context

Han Wei
Han Wei
Zhang Zhengdong
Zhang Zhengdong
Yu Jiahui
Yu Jiahui
Qin James
Qin James
Gulati Anmol
Gulati Anmol

INTERSPEECH, pp. 3610-3614, 2020.

Cited by: 30|Views83
EI

Abstract:

Convolutional neural networks (CNN) have shown promising results for end-to-end speech recognition, albeit still behind other state-of-the-art methods in performance. In this paper, we study how to bridge this gap and go beyond with a novel CNN-RNN-transducer architecture, which we call ContextNet. ContextNet features a fully convolutio...More

Code:

Data:

Your rating :
0

 

Tags
Comments