Speech Enhancement with Variational Autoencoders and Alpha-stable Distributions

This paper focuses on single-channel semi-supervised speech enhancement. We learn a speaker-independent deep generative speech model using the framework of variational autoencoders. The noise model remains unsupervised because we do not assume prior knowledge of the noisy recording environment. In t...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Proceedings of the ... IEEE International Conference on Acoustics, Speech and Signal Processing (1998) s. 541 - 545
Hlavní autoři: Leglaive, Simon, Simsekli, Umut, Liutkus, Antoine, Girin, Laurent, Horaud, Radu
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.05.2019
Témata:
alpha-stable distribution
Context modeling
Deep learning
Expectation-maximization algorithms
Monte Carlo expectation-maximization
Monte Carlo methods
Noise measurement
Speech enhancement
Time-frequency analysis
variational autoencoders
ISSN:2379-190X
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:This paper focuses on single-channel semi-supervised speech enhancement. We learn a speaker-independent deep generative speech model using the framework of variational autoencoders. The noise model remains unsupervised because we do not assume prior knowledge of the noisy recording environment. In this context, our contribution is to propose a noise model based on alpha-stable distributions, instead of the more conventional Gaussian non-negative matrix factorization approach found in previous studies. We develop a Monte Carlo expectation-maximization algorithm for estimating the model parameters at test time. Experimental results show the superiority of the proposed approach both in terms of perceptual quality and intelligibility of the enhanced speech signal.
ISSN:2379-190X
DOI:10.1109/ICASSP.2019.8682546