Improving Transformer Based End-to-End Code-Switching Speech Recognition Using Language Identification

Improving Transformer Based End-to-End Code-Switching Speech Recognition Using Language Identification

A Recurrent Neural Networks (RNN) based attention model has been used in code-switching speech recognition (CSSR). However, due to the sequential computation constraint of RNN, there are stronger short-range dependencies and weaker long-range dependencies, which makes it hard to immediately switch l...

Full description

Bibliographic Details
Main Authors: Zheying Huang, Pei Wang, Jian Wang, Haoran Miao, Ji Xu, Pengyuan Zhang
Format: Article
Language:English
Published: MDPI AG 2021-09-01
Series:Applied Sciences
Subjects:
speech recognition
code-switching
Transformer
multi-task learning
language identification
Online Access:https://www.mdpi.com/2076-3417/11/19/9106

Similar Items

Similar Items