Papers
arxiv:2309.08030

AV2Wav: Diffusion-Based Re-synthesis from Continuous Self-supervised Features for Audio-Visual Speech Enhancement

Published on Sep 14, 2023
Authors:
,
,

Abstract

AV2Wav, an audio-visual speech enhancement method using diffusion models and AV-HuBERT representations, surpasses masking baselines in both automatic metrics and human perception, generating clean speech from noisy AV data.

Speech enhancement systems are typically trained using pairs of clean and noisy speech. In audio-visual speech enhancement (AVSE), there is not as much ground-truth clean data available; most audio-visual datasets are collected in real-world environments with background noise and reverberation, hampering the development of AVSE. In this work, we introduce AV2Wav, a resynthesis-based audio-visual speech enhancement approach that can generate clean speech despite the challenges of real-world training data. We obtain a subset of nearly clean speech from an audio-visual corpus using a neural quality estimator, and then train a diffusion model on this subset to generate waveforms conditioned on continuous speech representations from AV-HuBERT with noise-robust training. We use continuous rather than discrete representations to retain prosody and speaker information. With this vocoding task alone, the model can perform speech enhancement better than a masking-based baseline. We further fine-tune the diffusion model on clean/noisy utterance pairs to improve the performance. Our approach outperforms a masking-based baseline in terms of both automatic metrics and a human listening test and is close in quality to the target speech in the listening test. Audio samples can be found at https://home.ttic.edu/~jcchou/demo/avse/avse_demo.html.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2309.08030
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2309.08030 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2309.08030 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2309.08030 in a Space README.md to link it from this page.

Collections including this paper 1