The i-vector model is widely used by the state-of-the-art speaker recognition system. We proposed a new Mahalanobis metric scoring learned from weighted pairwise constraints (WPCML), which use the different weights for the empirical error of the similar and dissimilar pairs. In the new i-vector space described by the metric, the distance between the same speaker’s i-vectors is small, while that of the different speakers’ is large. In forming the training set, we use the traditional way in random fashion and develop a new nearest distance based way. The results on the NIST 2008 telephone data shown that our model can get better performance than the classical cosine similarity scoring. When using the nearest distance based way to form the training set, our model is better than the state-of-the-art PLDA. And the results on the NIST 2014 i-vector challenge show that our model is also better than the PLDA.
Cite as: Lei, Z., Wan, Y., Luo, J., Yang, Y. (2016) Mahalanobis Metric Scoring Learned from Weighted Pairwise Constraints in I-Vector Speaker Recognition System. Proc. Interspeech 2016, 1815-1819, doi: 10.21437/Interspeech.2016-1071
@inproceedings{lei16_interspeech,
author={Zhenchun Lei and Yanhong Wan and Jian Luo and Yingen Yang},
title={{Mahalanobis Metric Scoring Learned from Weighted Pairwise Constraints in I-Vector Speaker Recognition System}},
year=2016,
booktitle={Proc. Interspeech 2016},
pages={1815--1819},
doi={10.21437/Interspeech.2016-1071}
}