Guardado en:
Detalles Bibliográficos
Autores principales: Ayilo, Jean-Eudes, Sadeghi, Mostafa, Serizel, Romain, Alameda-Pineda, Xavier
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:https://arxiv.org/abs/2601.09931
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916041963077632
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 addresses unsupervised diffusion-based single-channel speech enhancement (SE). Prior work in this direction combines a score-based diffusion model trained on clean speech with a Gaussian noise model whose covariance is structured by non-negative matrix factorization (NMF). This combination is used within an iterative expectation-maximization (EM) scheme, in which a diffusion-based posterior-sampling E-step estimates the clean speech. We first revisit this framework and propose to explicitly model both speech and acoustic noise as latent variables, jointly sampling them in the E-step instead of sampling speech alone as in previous approaches. We then introduce a new semi-supervised SE framework that replaces the NMF noise prior with a diffusion-based noise model, learned jointly with the speech prior in a single conditional score model. Within this framework, we derive two variants: one that implicitly accounts for noise and one that explicitly treats noise as a latent variable. Experiments on WSJ0-QUT and VoiceBank-DEMAND show that explicit noise modeling systematically improves SE performance for both NMF-based and diffusion-based noise priors. Under matched conditions, the diffusion-based noise model attains the best overall quality and intelligibility among unsupervised methods, while under mismatched conditions the proposed NMF-based explicit-noise framework is more robust and suffers less degradation than several supervised baselines. Code, demo, and supplementary materials are publicly available.
format Preprint
id arxiv_https___arxiv_org_abs_2601_09931
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Diffusion-based Frameworks for Unsupervised Speech Enhancement
Ayilo, Jean-Eudes
Sadeghi, Mostafa
Serizel, Romain
Alameda-Pineda, Xavier
Sound
This paper addresses unsupervised diffusion-based single-channel speech enhancement (SE). Prior work in this direction combines a score-based diffusion model trained on clean speech with a Gaussian noise model whose covariance is structured by non-negative matrix factorization (NMF). This combination is used within an iterative expectation-maximization (EM) scheme, in which a diffusion-based posterior-sampling E-step estimates the clean speech. We first revisit this framework and propose to explicitly model both speech and acoustic noise as latent variables, jointly sampling them in the E-step instead of sampling speech alone as in previous approaches. We then introduce a new semi-supervised SE framework that replaces the NMF noise prior with a diffusion-based noise model, learned jointly with the speech prior in a single conditional score model. Within this framework, we derive two variants: one that implicitly accounts for noise and one that explicitly treats noise as a latent variable. Experiments on WSJ0-QUT and VoiceBank-DEMAND show that explicit noise modeling systematically improves SE performance for both NMF-based and diffusion-based noise priors. Under matched conditions, the diffusion-based noise model attains the best overall quality and intelligibility among unsupervised methods, while under mismatched conditions the proposed NMF-based explicit-noise framework is more robust and suffers less degradation than several supervised baselines. Code, demo, and supplementary materials are publicly available.
title Diffusion-based Frameworks for Unsupervised Speech Enhancement
topic Sound
url https://arxiv.org/abs/2601.09931