Speaker Recognition using Gaussian Mixture Model

Abstract

Speaker recognition is a biometric operation of accepting a claimed person based on analyzing his spoken utterance. A text Independent speaker recognition system based on Gaussian Mixture Model (GMM) was developed with a specific focus on the use of a Voice Activated Detector (VAD) algorithm in the training and testing phases with a comparison between high and low quefrency coefficients provided by the Mel Frequency Cepstral Coefficients (MFCC). At the training level, a modified Estimation/Maximization (EM) algorithm is used. It is less prone to get trapped around a local maximum and so, it will have more chance to converge to the global maximum of the model. A new method of background speaker's model selection based on the identification results is also presented. High identification rate, low False Rejection (FR) and low False Acceptance (FA) are the most important parameters of the system design