Speaker verification using normalized log-likelihood score

In this correspondence, we propose a new scoring method for speaker verification called the normalized log-likelihood score. This method is derived from the Bayes test for minimum risk by the assumption of two hypotheses-the actual speaker is the claimed speaker or the actural speaker is an impostor-to attain the objective of minimizing the probability of error, The performance of this new scoring function used in speaker verification is examined by a series of experiments. For a 100-speaker database of isolated single digits, the equal error rate obtained by the normalized log-likelihood scoring method can be significantly decreased from 11.65 to 3.65% for the closed set test and from 12.30 to 8.22% for the open set test, as compared with those obtained by the conventional scoring method.