Audio-Visual Speech Enhancement with Score-Based Generative Models
Abstract
This paper introduces an audio-visual speech enhancement system that leverages score-based generative models, also known as diffusion models, conditioned on visual information. In particular, we exploit audio-visual embeddings obtained from a self-super\-vised learning model that has been fine-tuned on lipreading. The layer-wise features of its transformer-based encoder are aggregated, time-aligned, and incorporated into the noise conditional score network. Experimental evaluations show that the proposed audio-visual speech enhancement system yields improved speech quality and reduces generative artifacts such as phonetic confusions with respect to the audio-only equivalent. The latter is supported by the word error rate of a downstream automatic speech recognition model, which decreases noticeably, especially at low input signal-to-noise ratios.
Cite
@article{arxiv.2306.01432,
title = {Audio-Visual Speech Enhancement with Score-Based Generative Models},
author = {Julius Richter and Simone Frintrop and Timo Gerkmann},
journal= {arXiv preprint arXiv:2306.01432},
year = {2023}
}
Comments
Submitted to ITG Conference on Speech Communication