Title :
Empirical mode decomposition for usable speech detection
Author :
Ghezaiel, W. ; Ben Slimane, Ahmed ; Ben Braiek, Ezzedine
Author_Institution :
CEREP-Ecole Sup. des Sci. et Tech. de Tunis, Tunis, Tunisia
Abstract :
Usable speech criteria are proposed to extract minimally corrupted speech for speaker identification in co-channel speech. This paper deals with a empirical mode decomposition for usable speech segments detection of co-channel speech. Usable speech detected could be processed by a speaker identification system. Experiment and simulation of this method is performed on TIMIT database.
Keywords :
speaker recognition; speech recognition; TIMIT database; cochannel speech; empirical mode decomposition; speaker identification system; usable speech detection; Approximation methods; Correlation; Distance measurement; Empirical mode decomposition; Speech; Speech processing; Wavelet transforms; co-channel speech; empirical mode decomposition; speaker identification; usable segment;
Conference_Titel :
Electrical Engineering and Software Applications (ICEESA), 2013 International Conference on
Conference_Location :
Hammamet
Print_ISBN :
978-1-4673-6302-0
DOI :
10.1109/ICEESA.2013.6578413
