The Intelligent Voice 2016 Speaker Recognition System

TL;DR

This paper describes the Intelligent Voice 2016 speaker recognition system designed to be robust across diverse languages with limited training data, utilizing advanced i-vector/PLDA technology for the NIST SRE challenge.

Contribution

It introduces a speaker recognition system optimized for heterogeneous languages and minimal training data, advancing robustness in real-world scenarios.

Findings

System achieved competitive results on NIST SRE 2016

Demonstrated robustness across diverse languages

Utilized state-of-the-art i-vector/PLDA approach

Abstract

This paper presents the Intelligent Voice (IV) system submitted to the NIST 2016 Speaker Recognition Evaluation (SRE). The primary emphasis of SRE this year was on developing speaker recognition technology which is robust for novel languages that are much more heterogeneous than those used in the current state-of-the-art, using significantly less training data, that does not contain meta-data from those languages. The system is based on the state-of-the-art i-vector/PLDA which is developed on the fixed training condition, and the results are reported on the protocol defined on the development set of the challenge.