VoiceFixer: Toward General Speech Restoration with Neural Vocoder

Haohe Liu, Qiuqiang Kong, Qiao Tian, Yan Zhao, DeLiang Wang, Chuanzeng Huang, Yuxuan Wang

Keywords: Speech Restoration, Neural Vocoder, Speech Denoising, Speech Declipping, Speech Dereverberation, Speech Super-resolution

Abstract: Speech restoration aims to remove distortions in speech signals. Prior methods mainly focus on single-task speech restoration (SSR), such as speech denoising or speech declipping. However, SSR systems only focus on one task and do not address the general speech restoration problem. In addition, previous SSR systems show limited performance in some speech restoration tasks such as speech super-resolution. To overcome those limitations, we propose a general speech restoration (GSR) task that attempts to remove multiple distortions simultaneously. Furthermore, we propose VoiceFixer, a generative framework to address the GSR task. VoiceFixer consists of an analysis stage and a synthesis stage to mimic the speech analysis and comprehension of the human auditory system. We employ a ResUNet to model the analysis stage and a neural vocoder to model the synthesis stage. We evaluate VoiceFixer with additive noise, room reverberation, low-resolution, and clipping distortions. Our baseline GSR model achieves a 0.499 higher mean opinion score (MOS) than the speech denoising SSR model. VoiceFixer further surpasses the GSR baseline model on the MOS score by 0.256. Moreover, we observe that VoiceFixer generalizes well to severely degraded real speech recordings, indicating its potential in restoring old movies and historical speeches.

One-sentence Summary: VoiceFixer is the first model to achieve general speech restoration by jointly performing speech denoising, dereverberation, declipping, and super-resolution.

Community Implementations: [ 5 code implementations](https://www.catalyzex.com/paper/arxiv:2109.13731/code)