Title :
Parameter Settings for Speaker Identification using Gaussian Mixture Model
Author :
Eskidere, O. ; Ertas, Figen
Author_Institution :
Uludag Univ. Teknik Bilimler MYO, Bursa, Turkey
Abstract :
In this paper, the impact of the number of Gaussian mixtures, the duration of training and testing sessions, and the number of speakers on speaker identification has been investigated using clean speech (TIMIT) and telephone speech (NTIMIT) databases. Employing the parameters that provide the maximum performance, 100% and 85.71% identification rates have been obtained for the TIMIT and NTIMIT databases, respectively.
Keywords :
Gaussian processes; speaker recognition; Gaussian mixture model; clean speech databases; speaker identification; telephone speech databases; Databases; Gaussian processes; Speech; Telephony; Testing;
Conference_Titel :
Signal Processing and Communications Applications, 2007. SIU 2007. IEEE 15th
Conference_Location :
Eskisehir
Print_ISBN :
1-4244-0719-2
Electronic_ISBN :
1-4244-0720-6
DOI :
10.1109/SIU.2007.4298590
