Year: 2021
Type: preprint
Abstract: Speech enhancement is an essential task of improving speech quality in noise scenario. Several state-of-the-art approaches have introduced visual information for speech enhancement,since the visual aspect of speech is essentially unaffected by acoustic environment. This paper proposes a novel frameworkthat involves visual information for speech enhancement, by in-corporating a Generative Adversarial Network (GAN). In par-ticular, the proposed visual speech enhancement GAN consistof two networks trained in adversarial manner, i) a generator that adopts multi-layer feature fusion convolution network to enhance input noisy speech, and ii) a discriminator that attemptsto minimize the discrepancy between the distributions of the clean speech signal and enhanced speech signal. Experiment re-sults demonstrated superior performance of the proposed modelagainst several state-of-the-art
Source: arXiv (Cornell University)
Authors: Xu, Xinmeng, Wang, Yang, Xu, Dongxiang, Peng, Yiyuan, Zhang, Cong, Jia, Jie, Chen, Binbin
Institution: Trinity College Dublin
Language: English
Topic: Speech and Audio Processing
Subfield: Signal Processing
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4300860529