Similarity normalization for speaker verification by fuzzy fusion

Similarity or likelihood normalization techniques are important for speaker verification systems as they help to alleviate the variations in the speec h signals. In the conventional normalization, the a priori probabilities of the cohort speakers are assumed to be equal. From this standpoint, we appl y the theory of fuzzy measure and fuzzy integral to combine the likelihood values of the cohort speakers in which the assumption of equal a priori pro babilities is relaxed. This approach replaces the conventional normalizatio n term by the fuzzy integral which acts as a non-linear fusion of the simil arity measures of an utterance assigned to the cohort speakers. We illustra te the performance of the proposed approach by testing the speaker verifica tion system with both the conventional and the fuzzy algorithms using the c ommercial speech corpus TI46. The results in terms of the equal error rates show that the speaker verification system using the fuzzy integral is more flexible and more favorable than the conventional normalization method. (C ) 1999 Pattern Recognition Society. Published by Elsevier Science Ltd. All rights reserved.