English

Fantastic 4 system for NIST 2015 Language Recognition Evaluation

Computation and Language 2016-02-08 v1

Abstract

This article describes the systems jointly submitted by Institute for Infocomm (I2^2R), 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).

Cite

@article{arxiv.1602.01929,
  title  = {Fantastic 4 system for NIST 2015 Language Recognition Evaluation},
  author = {Kong Aik Lee and Ville Hautamäki and Anthony Larcher and Wei Rao and Hanwu Sun and Trung Hieu Nguyen and Guangsen Wang and Aleksandr Sizov and Ivan Kukanov and Amir Poorjam and Trung Ngo Trong and Xiong Xiao and Cheng-Lin Xu and Hai-Hua Xu and Bin Ma and Haizhou Li and Sylvain Meignier},
  journal= {arXiv preprint arXiv:1602.01929},
  year   = {2016}
}

Comments

Technical report for NIST LRE 2015 Workshop

R2 v1 2026-06-22T12:44:04.400Z