Fantastic 4 system for NIST 2015 Language Recognition Evaluation

TL;DR

This paper presents a fusion-based language recognition system for the 2015 NIST LRE, combining multiple sub-systems and classifiers to improve detection accuracy.

Contribution

It introduces a multi-system fusion approach using diverse features and classifiers for language recognition in the NIST 2015 evaluation.

Findings

Fusion of nine sub-systems enhances performance.

Multiple classifiers improve language detection accuracy.

System achieves competitive results in NIST LRE 2015.

Abstract

This article describes the systems jointly submitted by Institute for Infocomm (I$^2$R), the Laboratoire d'Informatique de l'Universit\'e du Maine (LIUM), Nanyang Technology University (NTU) and the University of Eastern Finland (UEF) for 2015 NIST Language Recognition Evaluation (LRE). The submitted system is a fusion of nine sub-systems based on i-vectors extracted from different types of features. Given the i-vectors, several classifiers are adopted for the language detection task including support vector machines (SVM), multi-class logistic regression (MCLR), Probabilistic Linear Discriminant Analysis (PLDA) and Deep Neural Networks (DNN).