This paper introduces a discriminative decision function scoring method for speaker recognition with the Joint Factor Analysis (JFA) system. In the scoring module of JFA system, an approximate form of the decision function is proposed. Based on the approximation, we present a discriminative decision function by re-estimating the contribution of each speech sound unit to the decision function. The discriminative decision function is used to exploit the individual Gaussian component for better classification. The experiments are carried out on the telephone-telephone core condition of NIST SRE2010. The experimental results show that the proposed scoring method outperforms the conventional frame-by-frame and integration scoring strategies, respectively providing up to 19% and 15% relative improvement.

Index Terms: speaker verification, joint Factor Analysis, discriminative decision function