Nonparametric feature normalization for SVM-based speaker verification

Abstract

We investigate several feature normalization and scaling approaches for use in speaker verification based on support vector machines. We are particularly interested in methods that are “knowledge-free” and work for a variety of features, leading us to investigate MLLR transforms, phone N-grams, prosodic sequences, and word N-gram features. Normalization methods studied include mean/variance normalization, TFLLR and TFLOG scaling, and a simple nonparametric approach: rank-normalization. We find that rank-normalization is uniformly competitive with other methods, and improves upon them in many cases.

Index Terms— Speaker verification, SVM modeling, feature normalization, kernel design.