Blind Spectral-GMM Estimation for Underdetermined Instantaneous Audio Source Separation

Simon Arberet 1 Alexey Ozerov 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 : The underdetermined blind audio source separation problem is often addressed in the time-frequency domain by assuming that each time-frequency point is an independently distributed random variable. Other approaches which are not blind assume a more structured model, like the Spectral Gaussian Mixture Models (Spectral-GMMs), thus exploiting statistical diversity of audio sources in the separation process. However, in this last approach, Spectral-GMMs are supposed to be learned from some training signals. In this paper, we propose a new approach for learning Spectral-GMMs of the sources without the need of using training signals. The proposed blind method significantly outperforms state-of-the-art approaches on stereophonic instantaneous music mixtures.
Liste complète des métadonnées

Cited literature [16 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-00482287
Contributor : Alexey Ozerov <>
Submitted on : Monday, May 10, 2010 - 10:50:27 AM
Last modification on : Wednesday, February 20, 2019 - 2:39:31 PM
Document(s) archivé(s) le : Thursday, September 16, 2010 - 1:50:23 PM

File

2009_ICA_ArberetOzerovVincentG...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00482287, version 1

Citation

Simon Arberet, Alexey Ozerov, Rémi Gribonval, Frédéric Bimbot. Blind Spectral-GMM Estimation for Underdetermined Instantaneous Audio Source Separation. International Conference on Independent Component Analysis and Blind Source Separation (ICA), Mar 2009, Paraty, Brazil. pp. 751 - 758. ⟨hal-00482287⟩

Share

Metrics

Record views

764

Files downloads

166