A Recurrent Variational Autoencoder for Speech Enhancement - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2020

A Recurrent Variational Autoencoder for Speech Enhancement


This paper presents a generative approach to speech enhancement based on a recurrent variational autoencoder (RVAE). The deep generative speech model is trained using clean speech signals only, and it is combined with a nonnegative matrix factorization noise model for speech enhancement. We propose a variational expectation-maximization algorithm where the encoder of the RVAE is finetuned at test time, to approximate the distribution of the latent variables given the noisy speech observations. Compared with previous approaches based on feed-forward fully-connected architectures, the proposed recurrent deep generative speech model induces a posterior temporal dynamic over the latent variables, which is shown to improve the speech enhancement results.
Fichier principal
Vignette du fichier
LAGH_2020.pdf (391.79 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-02329000 , version 1 (23-10-2019)
hal-02329000 , version 2 (07-02-2020)



Simon Leglaive, Xavier Alameda-Pineda, Laurent Girin, Radu Horaud. A Recurrent Variational Autoencoder for Speech Enhancement. ICASSP 2020 - IEEE International Conference on Acoustics, Speech and Signal Processing, IEEE, May 2020, Barcelone (virtual), Spain. pp.371-375, ⟨10.1109/ICASSP40776.2020.9053164⟩. ⟨hal-02329000v2⟩
452 View
1238 Download



Gmail Facebook X LinkedIn More