A Speech Recognition Model Building Method Combined Dynamic Convolution and Multi-Head Self-Attention Mechanism
The Conformer enhanced Transformer by using convolution serial connected to the multi-head self-attention (MHSA). The method strengthened the local attention calculation and obtained a better effect in auto speech recognition. This paper proposes a hybrid attention mechanism which combines the dynam...
Main Authors: | Wei Liu, Jiaming Sun, Yiming Sun, Chunyi Chen |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-05-01
|
Series: | Electronics |
Subjects: | |
Online Access: | https://www.mdpi.com/2079-9292/11/10/1656 |
Similar Items
-
Speech Emotion Recognition Using Convolution Neural Networks and Multi-Head Convolutional Transformer
by: Rizwan Ullah, et al.
Published: (2023-07-01) -
Head Fusion:A Method to Improve Accuracy and Robustness of Speech Emotion Recognition
by: XU Ming-ke, ZHANG Fan
Published: (2022-07-01) -
NSE-CATNet: Deep Neural Speech Enhancement Using Convolutional Attention Transformer Network
by: Nasir Saleem, et al.
Published: (2023-01-01) -
LAS-Transformer: An Enhanced Transformer Based on the Local Attention Mechanism for Speech Recognition
by: Pengbin Fu, et al.
Published: (2022-05-01) -
Speech Emotion Recognition Based on Self-Attention Weight Correction for Acoustic and Text Features
by: Jennifer Santoso, et al.
Published: (2022-01-01)