Semi-supervised multichannel speech enhancement with variational autoencoders and non-negative matrix factorization

Multichannel speech enhancement Monte Carlo expectation-maximization variational autoencoders non-negative matrix factorization local Gaussian modeling

Domains

Engineering Sciences [physics] Signal and Image processing Computer Science [cs] Neural and Evolutionary Computing [cs.NE]

Fichier principal

LGH-icassp2019.pdf (501.91 Ko)

Origin : Files produced by the author(s)

Simon Leglaive : Connect in order to contact the contributor

https://hal.inria.fr/hal-02005102

Submitted on : Tuesday, April 30, 2019-3:48:09 PM

Last modification on : Wednesday, February 8, 2023-10:27:46 AM

Dates and versions

hal-02005102 , version 1 (08-02-2019)

hal-02005102 , version 2 (30-04-2019)

Identifiers

HAL Id : hal-02005102 , version 2
DOI : 10.1109/ICASSP.2019.8683704

Cite

Simon Leglaive, Laurent Girin, Radu Horaud. Semi-supervised multichannel speech enhancement with variational autoencoders and non-negative matrix factorization. ICASSP 2019 - IEEE International Conference on Acoustics, Speech and Signal Processing, May 2019, Brighton, United Kingdom. pp.101-105, ⟨10.1109/ICASSP.2019.8683704⟩. ⟨hal-02005102v2⟩

Export

BibTeX TEI Dublin Core DC Terms EndNote Datacite

Collections

UGA CNRS INRIA GIPSA GIPSA-DPC LJK LJK_GI LJK_GI_PERCEPTION GIPSA-CRISSP INRIA2 EC_LYON_STRICT

248 View

628 Download