Salvato in:
Dettagli Bibliografici
Autori principali: Ayilo, Jean-Eudes, Sadeghi, Mostafa, Serizel, Romain, Alameda-Pineda, Xavier
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2410.05301
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913650680266752
author Ayilo, Jean-Eudes
Sadeghi, Mostafa
Serizel, Romain
Alameda-Pineda, Xavier
author_facet Ayilo, Jean-Eudes
Sadeghi, Mostafa
Serizel, Romain
Alameda-Pineda, Xavier
contents This paper proposes a new unsupervised audio-visual speech enhancement (AVSE) approach that combines a diffusion-based audio-visual speech generative model with a non-negative matrix factorization (NMF) noise model. First, the diffusion model is pre-trained on clean speech conditioned on corresponding video data to simulate the speech generative distribution. This pre-trained model is then paired with the NMF-based noise model to estimate clean speech iteratively. Specifically, a diffusion-based posterior sampling approach is implemented within the reverse diffusion process, where after each iteration, a speech estimate is obtained and used to update the noise parameters. Experimental results confirm that the proposed AVSE approach not only outperforms its audio-only counterpart but also generalizes better than a recent supervised-generative AVSE method. Additionally, the new inference algorithm offers a better balance between inference speed and performance compared to the previous diffusion-based method. Code and demo available at: https://jeaneudesayilo.github.io/fast_UdiffSE
format Preprint
id arxiv_https___arxiv_org_abs_2410_05301
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Diffusion-based Unsupervised Audio-visual Speech Enhancement
Ayilo, Jean-Eudes
Sadeghi, Mostafa
Serizel, Romain
Alameda-Pineda, Xavier
Sound
Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
Audio and Speech Processing
Signal Processing
This paper proposes a new unsupervised audio-visual speech enhancement (AVSE) approach that combines a diffusion-based audio-visual speech generative model with a non-negative matrix factorization (NMF) noise model. First, the diffusion model is pre-trained on clean speech conditioned on corresponding video data to simulate the speech generative distribution. This pre-trained model is then paired with the NMF-based noise model to estimate clean speech iteratively. Specifically, a diffusion-based posterior sampling approach is implemented within the reverse diffusion process, where after each iteration, a speech estimate is obtained and used to update the noise parameters. Experimental results confirm that the proposed AVSE approach not only outperforms its audio-only counterpart but also generalizes better than a recent supervised-generative AVSE method. Additionally, the new inference algorithm offers a better balance between inference speed and performance compared to the previous diffusion-based method. Code and demo available at: https://jeaneudesayilo.github.io/fast_UdiffSE
title Diffusion-based Unsupervised Audio-visual Speech Enhancement
topic Sound
Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
Audio and Speech Processing
Signal Processing
url https://arxiv.org/abs/2410.05301