SUT System Description for NIST SRE 2016

TL;DR

This paper details the SUT team's system submission for NIST SRE 2016, covering data, front-end processing, model training, and evaluation results, providing a comprehensive overview of their speaker recognition system.

Contribution

It offers a complete description of the system components and training procedures used in the NIST SRE 2016 submission by Sharif University of Technology.

Findings

Reported results on SRE16 dataset

Analyzed system performance and components

Described effective preconditioning methods

Abstract

This paper describes the submission to fixed condition of NIST SRE 2016 by Sharif University of Technology (SUT) team. We provide a full description of the systems that were included in our submission. We start with an overview of the datasets that were used for training and development. It is followed by describing front-ends which contain different VAD and feature types. UBM and i-vector extractor training are the next details in this paper. As one of the important steps in system preparation, preconditioning the i-vectors are explained in more details. Then, we describe the classifier and score normalization methods. And finally, some results on SRE16 evaluation dataset are reported and analyzed.