direkt zum Inhalt springen

direkt zum Hauptnavigationsmenü

Sie sind hier

TU Berlin

Inhalt des Dokuments

All Publications

Convolutive Decorrelation Procedures for Blind Source Separation
Citation key Vollgraf2000
Author Vollgraf, R. and Stetter, M. and Obermayer, K.
Title of Book Int. Workshop on Independent Component Analysis and Blind Signal Separation
Pages 515 – 520
Year 2000
Editor P. Pajunen and J. Karhunen
Abstract Convolutive decorrelation algorithms form a class of powerful algorithms for blind source separation. In contrast to ICA, they are based on vanishing second order cross correlation functions between sources. We provide an analyze an unifying approach for convolutive decorrelation procedures. The convolutive decorrelation procedures impose the problem of simultaneously diagonalizing a number of covariance matrices. We examine different cost functions for simultaneous diagonalization with respect to the demixing matrix. It turns out, that best performance is achieved for a cost function, that takes the squared sum of the off diagonal elements after the diagonal elements were normalized to unity. We then provide criteria for convolution kernels, that are optimal for noise robustness and which can guarantee positive definite covariance matrices, which are important for reliable convergence.
Link to publication Download Bibtex entry

Zusatzinformationen / Extras

Quick Access:

Schnellnavigation zur Seite über Nummerneingabe

Auxiliary Functions