Learning and controlling the source-filter representation of speech with a variational autoencoder

Saved in:

Bibliographic Details
Published in:	Speech Communication Vol. 148; pp. 53 - 65
Main Authors:	Sadok, Samir, Leglaive, Simon, Girin, Laurent, Alameda-Pineda, Xavier, Seguier, Renaud
Format:	Journal Article
Language:	Japanese
Published:	Elsevier BV 01.03.2023
Subjects:	[INFO.INFO-AI] Computer Science [cs]/Artificial Intelligence [cs.AI] [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG] [INFO.INFO-SD] Computer Science [cs]/Sound [cs.SD] [SPI.SIGNAL] Engineering Sciences [physics]/Signal and Image processing Audio and Speech Processing (eess.AS) Computer Science - Machine Learning Computer Science - Sound Deep generative models Electrical Engineering and Systems Science - Audio and Speech Processing FOS: Computer and information sciences FOS: Electrical engineering, electronic engineering, information engineering Machine Learning (cs.LG) Representation learning Sound (cs.SD) Source-filter model Variational autoencoder
ISSN:	0167-6393
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
ISSN:	0167-6393
DOI:	10.48550/arxiv.2204.07075