Text-independent speaker verification using support vector machines

In this article we address the issue of using the Support Vector Learning technique in combination with the currently well performing Gaussian Mixture Models (GMM) for speaker verification experiments. Support Vector Machines (SVM) is a new and very promising technique in statistical learning theory. Recently this technique produced very interesting results in image processing [1] [2] [3], and for the fusion of the experts in biometric authentication [4]. The SVM were already applied for speaker identification purpose, in [5] and [6]. In these applications, the frames computed on the speakers’ speech signal are given as input vectors to train the speaker specific SVM’s. In this work, we propose a new feature representation based on GMM to construct the input vectors to train the SVM to discriminate the true-target speaker access class from the non-target speaker access class. The results obtained with this hybrid GMM-SVM technique are compared to the classical Log-Likelihood Ratio (LLR) technique, on a sub-set of NIST’99 evaluation data which is a part of the Switchboard corpus. The influence of the hnorm normalization is also studied. In all the cases, the proposed systems using SVM outperform the classical LLR based systems.