Blind source separation in time frequency domain using contrast functions

Bouchouata, Abdelkrim

dc.contributor.author	Bouchouata, Abdelkrim
dc.contributor.other	Belouchrani, Adel, Directeur de thès
dc.date.accessioned	2020-12-17T14:34:27Z
dc.date.available	2020-12-17T14:34:27Z
dc.date.issued	2010
dc.identifier.other	M003410
dc.identifier.uri	http://repository.enp.edu.dz/xmlui/handle/123456789/869
dc.description	Mémoire de Magister : Electronique : Alger, Ecole Nationale Polytechnique : 2010	fr_FR
dc.description.abstract	This thesis presents the implementation of new blind source separation techniques exploiting the time-frequency signatures of the source signals. The proposed approach relies on time-frequency distributions (TFD). Two TFDbased contrast functions are presented for non-stationary sources. Iterative algorithms using the relative gradient technique are used to optimize the proposed functions and perform source separaration	fr_FR
dc.language.iso	en	fr_FR
dc.publisher	Ecole nationale polytechnique	fr_FR
dc.relation.ispartofseries	Electronique;
dc.subject	Blind source separation	fr_FR
dc.subject	Time-frequency distributions	fr_FR
dc.subject	Nonstationary signals	fr_FR
dc.subject	Iterative algorithms	fr_FR
dc.subject	Contrast functions	fr_FR
dc.title	Blind source separation in time frequency domain using contrast functions	fr_FR
dc.type	Thesis	fr_FR