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...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Proceedings of the ... IEEE International Conference on Acoustics, Speech and Signal Processing (1998) S. 541 - 545
Hauptverfasser:	Leglaive, Simon, Simsekli, Umut, Liutkus, Antoine, Girin, Laurent, Horaud, Radu
Format:	Tagungsbericht
Sprache:	Englisch
Veröffentlicht:	IEEE 01.05.2019
Schlagworte:	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
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!