Multi-objective Optimization Training of PLDA for Speaker Verification

Liang He; Xianhong Chen; Can Xu; Jia Liu

ICASSP 2019accepted0 citations

Multi-objective Optimization Training of PLDA for Speaker Verification

Liang He, Xianhong Chen, Can Xu, Jia Liu

Abstract

Most current state-of-the-art text-independent speaker verifi-cation systems take probabilistic linear discriminant analysis (PLDA) as their backend classifiers. The parameters of PL-DA are often estimated by maximizing the objective function, which focuses on increasing the value of log-likelihood function, but ignoring the distinction between speakers. In order to better distinguish speakers, we propose a multi-objective optimization training for PLDA. Experiment results show that the proposed method has more than 10% relative performance improvement in both EER and MinDCF on the NIST SRE14 i-vector challenge dataset, and about 20% relative performance improvement in EER on the MCE18 dataset.

BibTeX

@inproceedings{icassp2019_multiobjectiveop,
  title = {Multi-objective Optimization Training of PLDA for Speaker Verification},
  author = {Liang He and Xianhong Chen and Can Xu and Jia Liu},
  booktitle = {ICASSP 2019},
  year = {2019}
}