Title :
Evaluation of GMM-based features for SVM speaker verification
Author :
Liu, Minghui ; Huang, Zhongwei
Author_Institution :
Phonetic Lab., Shenzhen Univ., Shenzhen
Abstract :
This paper compares several feature extraction approaches based on Gaussian mixture model (GMM) for support vector machine (SVM) in text-independent speaker verification. Because of excellent scalability, GMM can be used to extract fixed number of typical feature vectors from various length speech data. Experiments with different GMM-based features in SVM speaker verification system were performed on the NISTpsila04 1side-1side database and compared with the baseline GMM-UBM.
Keywords :
Gaussian processes; feature extraction; speaker recognition; support vector machines; Gaussian mixture model; NISTpsila04 1side-1side database; feature extraction approaches; support vector machine; text-independent speaker verification; Automation; Data mining; Feature extraction; Intelligent control; Laboratories; Scalability; Spatial databases; Speech; Support vector machine classification; Support vector machines; Gaussian Mixture Model; SVM; Speaker verification; feature extraction;
Conference_Titel :
Intelligent Control and Automation, 2008. WCICA 2008. 7th World Congress on
Conference_Location :
Chongqing
Print_ISBN :
978-1-4244-2113-8
Electronic_ISBN :
978-1-4244-2114-5
DOI :
10.1109/WCICA.2008.4593744
