A New Two-stage Scoring Normalization Approach to Speaker Verification

In speaker verification, the cohort and world models have been separately used for scoring normalization. In this work, we embed the two models in elliptical basis function networks and propose a two-stage decision procedure for improving verification performance. The procedure begins with normalization of an utterance by a world model. If the difference between the resulting score and a world threshold is sufficiently large, the claimant is accepted or rejected immediately. Otherwise, the score will be normalized by a cohort model, and the resulting score will be compared with a cohort threshold to make a final accept/reject decision. Experimental evaluations based on the YOHO corpus suggest that the two-stage method achieves a lower error rate as compared to the case where only one background model is used.