Speech Enhancement Performance Based on the MANNER Network Using Feature Fusion

Speech Enhancement Performance Based on the MANNER Network Using Feature Fusion

The problems that the multi-view attention network for noise erasure (MANNER) cannot take into account are the local and global features in the speech enhancement of long sequences. An attention and feature fusion MANNER (AF-MANNER) network is proposed, which improves the multi-view attention (MA) m...

Full description

Bibliographic Details
Main Authors: Shijie Wang, Ji Li, Lei Shao, Hongli Liu, Lihua Zhu, Xiaochen Zhu
Format: Article
Language:English
Published: MDPI AG 2023-04-01
Series:Electronics
Subjects:
speech enhancement
feature fusion
attention mechanisms
U-Net
MANNER
Online Access:https://www.mdpi.com/2079-9292/12/8/1768

Internet

https://www.mdpi.com/2079-9292/12/8/1768

Similar Items