Using second order statistics for text independent speaker verification

This paper describes a computationally simple method to perform text independent speaker verification using second order statistics. The suggested method, called Utterance Level Scoring (ULS), allows obtaining a normalized score using a single pass through the frames of the tested utterance. The utterance sample covariance is first calculated and then compared to the speaker covariance using a distortion measure. Subsequently, a distortion measure between the utterance covariance and the sample covariance of data taken from different speakers is used to normalize the score. Experimental results from the 2000 NIST speaker recognition evaluation are presented for ULS, used with different distortion measures, and for a GMM system. The results show a relative degradation of 40% in accuracy with respect to GMM, indicating ULS as a viable alternative to GMM whenever computational complexity and verification accuracy needs to be traded. ULS is intended to be used as a first stage of an efficient open set speaker identification system. All speakers will be first scored by ULS and then the top scoring speakers will be scored again using GMM.