LAS-Transformer: An Enhanced Transformer Based on the Local Attention Mechanism for Speech Recognition

LAS-Transformer: An Enhanced Transformer Based on the Local Attention Mechanism for Speech Recognition

Recently, Transformer-based models have shown promising results in automatic speech recognition (ASR), outperforming models based on recurrent neural networks (RNNs) and convolutional neural networks (CNNs). However, directly applying a Transformer to the ASR task does not exploit the correlation am...

Full description

Bibliographic Details
Main Authors: Pengbin Fu, Daxing Liu, Huirong Yang
Format: Article
Language:English
Published: MDPI AG 2022-05-01
Series:Information
Subjects:
end-to-end model
speech recognition
Transformer
local attention
Online Access:https://www.mdpi.com/2078-2489/13/5/250

Internet

https://www.mdpi.com/2078-2489/13/5/250

Similar Items