Xmu-Ts Systems For Nist Sre19 Cts Challenge

In this paper, we present our submitted XMU-TS system for NIST SRE19 CTS Challenge. The evaluation of this year only offers the open training condition. With the large amounts of data assimilated into training set, the diversity of training data sources inevitably leads to domain mismatch, which becomes a key factor affecting the system performance. In order to solve this problem, we have made a lot of attempts. Based on the x-vector framework, we used different network structures, and tried to modify the performance of factorized time delay deep neural network (F-TDNN) and residual network (ResNet). In addition, in the back-end classifier, we used domain adaption to eliminate the impact of domain mismatch. Finally, we employed Adaptive Symmetric Score Normalization (AS-Norm) for score normalization to adjust the fractional distribution space. These attempts have enriched the diversity of our systems, enabling the fusion system to complement each subsystem and improve the final submission performace.