Multiple background models for speaker verification using the concept of vocal tract length and MLLR super-vector

Abstract

In this paper, we investigate the use of Multiple Background Models (M-BMs) in Speaker Verification (SV). We cluster the speakers using either their Vocal Tract Lengths (VTLs) or by using their speaker specific Maximum Likelihood Linear Regression (MLLR) super-vector, and build a separate Background Model (BM) for each such cluster. We show that the use of M-BMs provide improved performance when compared to the use of a single/gender wise Universal Background Model (UBM). While the computational complexity during test remains same for both M-BMs and UBM, M-BMs require switching of models depending on the claimant and also score-normalization becomes difficult. To overcome these problems, we propose a novel method which aggregates the information from Multiple Background Models into a single gender independent UBM and is inspired by conventional Feature Mapping (FM) technique. We show that using this approach, we get improvement over the conventional UBM method, and yet this approach also permits easy use of score-normalization techniques. The proposed method provides relative improvement in Equal-Error Rate (EER) by 13.65 % in the case of VTL clustering, and 15.43 % in the case of MLLR super-vector when compared to the conventional single UBM system. When AT-norm score-normalization is used then the proposed method provided a relative improvement in EER of 20.96 % for VTL clustering and 22.48 % for MLLR super-vector based clustering. Furthermore, the proposed method is compared with the gender dependent speaker verification system using Gaussian Mixture Model-Support Vector Machines (GMM-SVM) super-vector linear kernel. The experimental results show that the proposed method perform better than gender dependent speaker verification system.