DocumentCode :
621973
Title :
Multi-resolution analysis by 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
fYear :
2013
fDate :
18-21 March 2013
Firstpage :
1
Lastpage :
5
Abstract :
Many applications of speech communication and speaker identification suffer from the problem of co-channel speech. This paper deals with a multi-resolution analysis by 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 evaluation of this method is performed on TIMIT database.
Keywords :
speaker recognition; TIMIT database; cochannel speech detection; empirical mode decomposition; multiresolution analysis; speaker identification; speech communication; usable speech detection; Correlation; Distance measurement; Empirical mode decomposition; Speech; Speech processing; Wavelet transforms; co-channel speech; empirical mode decomposition; multi-resolution; speaker identification; usable segment;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Systems, Signals & Devices (SSD), 2013 10th International Multi-Conference on
Conference_Location :
Hammamet
Print_ISBN :
978-1-4673-6459-1
Electronic_ISBN :
978-1-4673-6458-4
Type :
conf
DOI :
10.1109/SSD.2013.6564031
Filename :
6564031
Link To Document :
بازگشت