A comparison between sequence kernels for SVM speaker verification

We present a comparative study of several SVM speaker verification (SV) systems based on sequence kernels: the GMM-supervectors kernel, the fisher kernel, the Generalized linear discriminant sequence (GLDS) kernel, our feature space normalized sequence (FSNS) kernel and a ldquonovelrdquo sequence kernel in SV, the correlation kernel. We also compare these SVM systems to the conventional generative UBM-GMM. We carry out experiments on the NIST´2005 SRE evaluation set. The results show that the FSNS system yields comparable performances to UBM-GMM and significantly outperforms GLDS. They also show that the GMM-supervectors system outperforms all the others. Finally, they show that the best performances are achieved by fusing the FSNS and the GMM-supervectors systems.