Conformer: Convolution-augmented Transformer for Speech Recognition

Gulati Anmol
Gulati Anmol
Qin James
Qin James
Parmar Niki
Parmar Niki
Yu Jiahui
Yu Jiahui
Han Wei
Han Wei
Wang Shibo
Wang Shibo
Zhang Zhengdong
Zhang Zhengdong

INTERSPEECH, pp. 5036-5040, 2020.

Cited by: 56|Views67
EI

Abstract:

Recently Transformer and Convolution neural network (CNN) based models have shown promising results in Automatic Speech Recognition (ASR), outperforming Recurrent neural networks (RNNs). Transformer models are good at capturing content-based global interactions, while CNNs exploit local features effectively. In this work, we achieve the...More

Code:

Data:

Your rating :
0

 

Tags
Comments