A weighted-variance variational autoencoder model for speech enhancement - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2022

A weighted-variance variational autoencoder model for speech enhancement

Résumé

We address speech enhancement based on variational autoencoders, which involves learning a speech prior distribution in the time-frequency (TF) domain. A zero-mean complex-valued Gaussian distribution is usually assumed for the generative model, where the speech information is encoded in the variance as a function of a latent variable. In contrast to this commonly used approach, we propose a weighted variance generative model, where the contribution of each spectrogram time-frame in parameter learning is weighted. We impose a Gamma prior distribution on the weights, which would effectively lead to a Student's t-distribution instead of Gaussian for speech generative modeling. We develop efficient training and speech enhancement algorithms based on the proposed generative model. Our experimental results on spectrogram auto-encoding and speech enhancement demonstrate the effectiveness and robustness of the proposed approach compared to the standard unweighted variance model.
Fichier principal
Vignette du fichier
main.pdf (245.18 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03833827 , version 1 (28-10-2022)
hal-03833827 , version 2 (20-09-2023)

Licence

Identifiants

Citer

Ali Golmakani, Mostafa Sadeghi, Xavier Alameda-Pineda, Romain Serizel. A weighted-variance variational autoencoder model for speech enhancement. 2022. ⟨hal-03833827v1⟩

Collections

GRID5000 SILECS
221 Consultations
86 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More