One microphone singing voice separation using source-adapted models

Alexey Ozerov 1, 2 Pierrick Philippe 2 Rémi Gribonval 1 Frédéric Bimbot 1
1 METISS - Speech and sound data modeling and processing
IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires, Inria Rennes – Bretagne Atlantique
Abstract : In this paper, the problem of one microphone source separation applied to singing voice extraction is studied. A probabilistic approach based on Gaussian Mixture Models (GMM) of the short time spectra of two sources is used. The question of source model adaptation is investigated in order to improve separation quality. A new adaptation method consisting in a filter adaptation technique via the Maximum Likelihood Linear Regression (MLLR) is presented with an associated filter-adapted training phase.
Complete list of metadatas

Cited literature [9 references]  Display  Hide  Download

https://hal.inria.fr/inria-00564491
Contributor : Rémi Gribonval <>
Submitted on : Wednesday, February 9, 2011 - 8:57:26 AM
Last modification on : Friday, November 16, 2018 - 1:22:34 AM
Long-term archiving on: Tuesday, May 10, 2011 - 2:49:43 AM

File

2005_WASPAA_OzerovEtlAl.pdf
Explicit agreement for this submission

Identifiers

Citation

Alexey Ozerov, Pierrick Philippe, Rémi Gribonval, Frédéric Bimbot. One microphone singing voice separation using source-adapted models. Applications of Signal Processing to Audio and Acoustics, 2005. IEEE Workshop on, Oct 2005, Mohonk Mountain House, New Paltz, New York, United States. pp.90--93, ⟨10.1109/ASPAA.2005.1540176⟩. ⟨inria-00564491⟩

Share

Metrics

Record views

603

Files downloads

430