Blind speech separation in convolutive mixtures using non-Gaussianity maximization and inverse filters

In this paper, we proposed the approach which combines inverse filter criteria with non-Gaussianity to separate convolutive mixtures of speech in the time domain. In this case, the proposed method first extract innovation processes of speech sources by non-Gaussianity maximization and then artificia...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Vuong-Hoang, N, Nguyen-Quoc, T, Tran-Hoai, L
Format: Tagungsbericht
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:In this paper, we proposed the approach which combines inverse filter criteria with non-Gaussianity to separate convolutive mixtures of speech in the time domain. In this case, the proposed method first extract innovation processes of speech sources by non-Gaussianity maximization and then artificially color them by re-coloration filters. Computer simulation experiments are presented to illustrate the proposed approach.
DOI:10.1109/ICCE.2010.5670708