I4U System Description for NIST SRE'20 CTS Challenge

TL;DR

This paper details the I4U system submission to the NIST SRE'20 CTS Challenge, highlighting collaborative efforts, system fusion, and standardized evaluation procedures to improve speaker recognition performance.

Contribution

It introduces a multi-team collaborative system fusion approach with standardized evaluation protocols for the NIST SRE'20 CTS Challenge.

Findings

Fusion of top-performing sub-systems improved recognition accuracy.

Standardized development and validation sets facilitated consistent evaluation.

Collaborative approach enhanced overall system robustness.

Abstract

This manuscript describes the I4U submission to the 2020 NIST Speaker Recognition Evaluation (SRE'20) Conversational Telephone Speech (CTS) Challenge. The I4U's submission was resulted from active collaboration among researchers across eight research teams - I$^2$R (Singapore), UEF (Finland), VALPT (Italy, Spain), NEC (Japan), THUEE (China), LIA (France), NUS (Singapore), INRIA (France) and TJU (China). The submission was based on the fusion of top performing sub-systems and sub-fusion systems contributed by individual teams. Efforts have been spent on the use of common development and validation sets, submission schedule and milestone, minimizing inconsistency in trial list and score file format across sites.