Improved GMM-UBM/SVM for speaker verification

Abstract

This paper combines Gaussian Mixture Model-Universal Background Model (GMM-UBM) and Support Vector Machine (SVM) through post processing the GMM-UBM scores of different dimension feature parameter with SVM in speaker verification. Because different dimension feature makes different contribution to recognition performance and SVM has good discriminability, this combining approach yields significant performance improvements on decisionmaking. Experiments on text-independent speaker verification in NIST'05 8conv4w-1conv4w data showed that the actual detection cost function (DCF) of the test system was reduced to 0.0290 from 0.0343. © 2006 IEEE.