VoiceFixer: Toward General Speech Restoration with Neural Vocoder
arXiv:2109.13731
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 enhancement 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.
References in corpus (22)
- Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
- Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation
- MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis
- FastSpeech: Fast, Robust and Controllable Text to Speech
- A multi-device dataset for urban acoustic scene classification
- DurIAN: Duration Informed Attention Network For Multimodal Synthesis
- AISHELL-3: A Multi-speaker Mandarin TTS Corpus and the Baselines
- Audio-Visual Speech Separation and Dereverberation with a Two-Stage Multimodal Network
- NU-Wave: A Diffusion Probabilistic Model for Neural Audio Upsampling
- DCCRN: Deep Complex Convolution Recurrent Network for Phase-Aware Speech Enhancement
- Improved Speech Enhancement with the Wave-U-Net
- A survey and an extensive evaluation of popular audio declipping methods
- Audio Super Resolution using Neural Networks
- Sparse Recovery and Dictionary Learning from Nonlinear Compressive Measurements
- On Filter Generalization for Music Bandwidth Extension Using Deep Neural Networks
- Channel-wise Subband Input for Better Voice and Accompaniment Separation on High Resolution Music
- NU-GAN: High resolution neural upsampling with GAN
- TFGAN: Time and Frequency Domain Based Generative Adversarial Network for High-fidelity Speech Synthesis
- Joint Echo Cancellation and Noise Suppression based on Cascaded Magnitude and Complex Mask Estimation
- Psychoacoustically Motivated Audio Declipping Based on Weighted l1 Minimization
- Image to Image Translation based on Convolutional Neural Network Approach for Speech Declipping
- Speech enhancement with weakly labelled data from AudioSet