Article
Version 1
Preserved in Portico This version is not peer-reviewed
CGA-MGAN: Metric GAN based on Convolution-augmented Gated Attention for Speech Enhancement
Version 1
: Received: 27 February 2023 / Approved: 27 February 2023 / Online: 27 February 2023 (09:24:31 CET)
A peer-reviewed article of this Preprint also exists.
Chen, H.; Zhang, X. CGA-MGAN: Metric GAN Based on Convolution-Augmented Gated Attention for Speech Enhancement. Entropy 2023, 25, 628. Chen, H.; Zhang, X. CGA-MGAN: Metric GAN Based on Convolution-Augmented Gated Attention for Speech Enhancement. Entropy 2023, 25, 628.
Abstract
In recent years, neural networks based on attention mechanisms have been increasingly widely used in speech recognition, separation, enhancement, and other fields. In particular, the convolution-augmented transformer has achieved good performance as it can combine the advantages of convolution and self-attention. Recently, the gated attention unit (GAU) has been proposed. Compared with the traditional multi-head self-attention, approaches with GAU are effective and computationally efficient. In this article, we propose a network for speech enhancement called CGA-MGAN, a kind of Metric GAN based on convolution-augmented gated attention. CGA-MGAN captures local and global correlations in speech signals at the same time through the fusion of convolution and gated attention units. Experiments on Voice Bank + DEMAND show that the CGA-MGAN we propose achieves an excellent performance (3.47 PESQ, 0.96 STOI, and 11.09dB SSNR) at a relatively small model size (1.14M).
Keywords
CGA-MGAN; Gated Attention Unit; Speech Enhancement
Subject
Computer Science and Mathematics, Information Systems
Copyright: This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Comments (0)
We encourage comments and feedback from a broad range of readers. See criteria for comments and our Diversity statement.
Leave a public commentSend a private comment to the author(s)
* All users must log in before leaving a comment
