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 VoiceFixer1, 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. The source code is available at https://github.com/haoheliu/voicefixer_main.
[1]
Jae S. Lim,et al.
Speech enhancement
,
1986,
ICASSP '86. IEEE International Conference on Acoustics, Speech, and Signal Processing.
[2]
Thomas Fang Zheng,et al.
Detection and reconstruction of clipped speech for speaker recognition
,
2015,
Speech Commun..
[3]
Albert S. Bregman,et al.
The Auditory Scene. (Book Reviews: Auditory Scene Analysis. The Perceptual Organization of Sound.)
,
1990
.
[4]
Pang Wei Koh,et al.
Temporal FiLM: Capturing Long-Range Sequence Dependencies with Feature-Wise Modulations
,
2019,
NeurIPS.
[5]
Yoshua Bengio,et al.
Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
,
2014,
ArXiv.
[6]
S. Doclo,et al.
JOINT DEREVERBERATION AND NOISE REDUCTION USING BEAMFORMING AND A SINGLE-CHANNEL SPEECH ENHANCEMENT SCHEME
,
2014
.