This paper presents an improved speaker recognition system for the summed channel evaluation tasks in the 2008 NIST SRE (SRE08) with multiple summed-channel excerpts for speaker training and one summed-channel excerpt for testing. The system includes three main modules in which a hybrid speaker purification and clustering algorithm is adopted to segregate the summed-channel speech, a common speaker identification is proposed by mapping multiple summed-channel excerpts for a common speaker cluster, and the GMM-SVM-NAP algorithm is used for the speaker recognition system. The system achieves an overall EER of 7.82% for all the trials and 4.19% for English trials in the SRE08 3summed-summed task.
Cite as: Sun, H., Ma, B. (2014) The NIST SRE summed channel speaker recognition system. Proc. Interspeech 2014, 1111-1114, doi: 10.21437/Interspeech.2014-285
@inproceedings{sun14_interspeech,
author={Hanwu Sun and Bin Ma},
title={{The NIST SRE summed channel speaker recognition system}},
year=2014,
booktitle={Proc. Interspeech 2014},
pages={1111--1114},
doi={10.21437/Interspeech.2014-285}
}