Discriminative Classifiers for Speaker Recognition

Due to the growing need for security applications, speaker recognition as the biometric task of authenticating a claimant by voice has currently become a focus of interest. In this book we present new approaches to integrate discriminative classifiers like Support Vector Machines (SVMs) and Sparse Kernel Logistic Regression (SKLR) into speaker recognition systems that are traditionally based on generative classifiers like Gaussian Mixture Models (GMMs). In a first approach for limited training data the discriminative classifiers are applied directly on feature vectors from parameterized speech frames and it is shown that both, SVM as well as SKLR outperform traditional methods. In the second approach a state-of-the-art speaker recognition system for large amount of training data is designed that combines Gaussian Mixture Models with discriminative classifiers. Furthermore, we investigate different feature extraction methods for speaker recognition on large amount of training data and it is shown that the application of fusion schemes that combine these subsystems yield a significant improvement of the recognition performance in comparison to the application of single subsystems.