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...
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: | |
Online Access: | https://www.mdpi.com/2076-3417/11/19/9106 |
Similar Items
-
Code-Switching in Automatic Speech Recognition: The Issues and Future Directions
by: Mumtaz Begum Mustafa, et al.
Published: (2022-09-01) -
Phonetic Variation Modeling and a Language Model Adaptation for Korean English Code-Switching Speech Recognition
by: Damheo Lee, et al.
Published: (2021-03-01) -
Improving N-Best Rescoring in Under-Resourced Code-Switched Speech Recognition Using Pretraining and Data Augmentation
by: Joshua Jansen van Vüren, et al.
Published: (2022-09-01) -
End-to-End Mandarin Speech Recognition Combining CNN and BLSTM
by: Dong Wang, et al.
Published: (2019-05-01) -
Improving End-to-End Models for Children’s Speech Recognition
by: Tanvina Patel, et al.
Published: (2024-03-01)