SVM Based Speaker Recognition Using Maximum a posteriori Linear Regression

Maximum likelihood linear regression (MLLR) is a widely used technique for speaker adaptation in large vocabulary speech recognition system. Recently, using MLLR transforms as features for SVM based speaker recognition tasks has been proposed, achieving performance comparable to that obtained with cepstral features. In this paper, we focus on calculating the transforms based on a GMM universal background model (UBM). Rather than estimating the transforms using maximum likelihood criterion, this paper describes a new feature extraction technique for speaker recognition based on maximum a posteriori linear regression (MAPLR), which uses maximum a posteriori (MAP) as estimation criterion. We perform experiments on a NIST SRE 2008 corpus. Experimental results show that the system based on MAPLR technique outperforms MLLR in the task of speaker recognition.