Unsupervised Speech Enhancement using Dynamical Variational Auto-Encoders

Dynamical variational autoencoders (DVAEs) are a class of deep generative models with latent variables, dedicated to model time series of high-dimensional data. DVAEs can be considered as extensions of the variational autoencoder (VAE) that include temporal dependencies between successive observed a...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2022-09
Hauptverfasser:	Bie, Xiaoyu, Leglaive, Simon, Alameda-Pineda, Xavier, Girin, Laurent
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms Coders Computer Science - Artificial Intelligence Computer Science - Learning Computer Science - Sound Machine learning Modelling Noise Sequences Speech Speech processing
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!