Kim, Hyung Yong and Yoon, Ji Won and Cheon, Sung Jun and Kang, Woo Hyun and Kim, Nam Soo (2021) A Multi-Resolution Approach to GAN-Based Speech Enhancement. Applied Sciences, 11 (2). p. 721. ISSN 2076-3417
applsci-11-00721-v2.pdf - Published Version
Download (1MB)
Abstract
Recently, generative adversarial networks (GANs) have been successfully applied to speech enhancement. However, there still remain two issues that need to be addressed: (1) GAN-based training is typically unstable due to its non-convex property, and (2) most of the conventional methods do not fully take advantage of the speech characteristics, which could result in a sub-optimal solution. In order to deal with these problems, we propose a progressive generator that can handle the speech in a multi-resolution fashion. Additionally, we propose a multi-scale discriminator that discriminates the real and generated speech at various sampling rates to stabilize GAN training. The proposed structure was compared with the conventional GAN-based speech enhancement algorithms using the VoiceBank-DEMAND dataset. Experimental results showed that the proposed approach can make the training faster and more stable, which improves the performance on various metrics for speech enhancement.
Item Type: | Article |
---|---|
Subjects: | Pacific Library > Engineering |
Depositing User: | Unnamed user with email support@pacificlibrary.org |
Date Deposited: | 19 Jan 2023 10:50 |
Last Modified: | 22 May 2024 09:58 |
URI: | http://editor.classicopenlibrary.com/id/eprint/163 |