Title :
Optimization of the number of Gaussian components for speaker identification
Author :
Cirigliano, R.R. ; Resende, F. G V, Jr.
Author_Institution :
Fed. Univ. of Rio de Janeiro, Rio de Janeiro
Abstract :
In this paper we present an algorithm that searches the optimal number of components for each speaker based on the rate between the maximum and the average distortion in each cell obtained through the k-means algorithm. The speakers are modeled by orthogonal GMM and each of them has a different number of components. The tests showed that the usage of this algorithm decreases the error rate in average 36.2% and also decreases the computational effort of the identification process in average 48% when compared to orthogonal GMM models.
Keywords :
Gaussian processes; speaker recognition; Gaussian components; average distortion; k-means algorithm; orthogonal GMM; speaker identification; Error analysis; Testing; GMM; Speaker identification; variable number of Gaussian components;
Conference_Titel :
Telecommunications Symposium, 2006 International
Conference_Location :
Fortaleza, Ceara
Print_ISBN :
978-85-89748-04-9
Electronic_ISBN :
978-85-89748-04-9
DOI :
10.1109/ITS.2006.4433310
