Complex nonconvex lp norm minimization for underdetermined source separation

Emmanuel Vincent 1
1 METISS - Speech and sound data modeling and processing
IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires, Inria Rennes – Bretagne Atlantique
Abstract : Underdetermined source separation methods often rely on the assumption that the time-frequency source coefficients are independent and Laplacian distributed. In this article, we extend these methods by assuming that these coefficients follow a generalized Gaussian prior with shape parameter p. We study mathematical and experimental properties of the resulting complex nonconvex lp norm optimization problem in a particular case and derive an efficient global optimization algorithm. We show that the best separation performance for three-source stereo convolutive speech mixtures is achieved for small p.
Liste complète des métadonnées

Cited literature [13 references]  Display  Hide  Download

https://hal.inria.fr/inria-00544203
Contributor : Emmanuel Vincent <>
Submitted on : Tuesday, December 7, 2010 - 2:54:24 PM
Last modification on : Thursday, March 21, 2019 - 2:20:42 PM
Document(s) archivé(s) le : Tuesday, March 8, 2011 - 4:28:58 AM

File

vincent_ICA07bis.pdf
Publisher files allowed on an open archive

Identifiers

  • HAL Id : inria-00544203, version 1

Citation

Emmanuel Vincent. Complex nonconvex lp norm minimization for underdetermined source separation. 7th Int. Conf. on Independent Component Analysis and Blind Source Separation (ICA), Sep 2007, London, United Kingdom. pp.430--437. ⟨inria-00544203⟩

Share

Metrics

Record views

330

Files downloads

609