Skip to Main Content
NIST Speaker Recognition Evaluations (NIST SRE), played a major role in the progress of text-independent speaker verification algorithms. Tübitak UEKAE - Sabancı University jointly participated in NIST SRE 2010. In this paper, the Gaussian Mixture Model Supervector - Support Vector Machine based speaker verification system developed for NIST SRE 2010 has been presented. A recipe has been given for the training of Universal Background Model which is an essential step for system's performance. Results of the Nuisance Attribute Projection algorithm integrated to the system after evaluation to suppress the session variabilities has also been presented.