Current best performing speaker recognition algorithms are based on Gaussian Mixture Models (GMM). Their results are not satisfactory for all experimental conditions, especially for the mismatched between train and test conditions. Support Vector Machine is a new and very promissing technique in statistical learning theory. Recently, this technique produced very interesting results in image processing and for the fusion of experts in biometric authentification. In this paper we address the issue of using the Support Vector Learning technique in combination with the currently well performing GMM models, in order to improve speaker verification results.

Full Paper

Bibliographic reference.  Kharroubi, Jamal / Petrovska-Delacretaz, Dijana / Chollet, Gerard (2001): "Combining GMM's with suport vector machines for text-independent speaker verification", In EUROSPEECH-2001, 1761-1764.