English

VSEGAN: Visual Speech Enhancement Generative Adversarial Network

Audio and Speech Processing 2022-04-21 v2 Sound Image and Video Processing

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

Keywords

Cite

@article{arxiv.2102.02599,
  title  = {VSEGAN: Visual Speech Enhancement Generative Adversarial Network},
  author = {Xinmeng Xu and Yang Wang and Dongxiang Xu and Yiyuan Peng and Cong Zhang and Jie Jia and Binbin Chen},
  journal= {arXiv preprint arXiv:2102.02599},
  year   = {2022}
}

Comments

Accepted by ICASSP 2022

R2 v1 2026-06-23T22:50:08.560Z