A Recurrent Variational Autoencoder for Speech Enhancement
Abstract
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 fine-tuned 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.
Cite
@article{arxiv.1910.10942,
title = {A Recurrent Variational Autoencoder for Speech Enhancement},
author = {Simon Leglaive and Xavier Alameda-Pineda and Laurent Girin and Radu Horaud},
journal= {arXiv preprint arXiv:1910.10942},
year = {2020}
}