Optimizing acoustic features for source cell-phone recognition using speech signals
Proceedings of the first ACM workshop on Information hiding and multimedia security
| Hi-index | 0.00 |
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 “novel” 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.