Comparison of the automatic speaker recognition performance over standard features

Abstract

This paper presents a study of speaker recognition accuracy depending on the choice of features, window width and model complexity. The standard features were considered, such as linear and perceptual prediction coefficients (LPC and PLP) and mel-frequency cepstral coefficients (MFCC). Gaussian mixture model (GMM), with the use of HTK tools, was chosen for speaker modelling. Speech database S70W100s120, recorded at the Electrical Engineering Department of Belgrade University, was used for purposes of system training and testing. Ten speaker models and the universal background model (UBM) were trained.