Multiobjective Optimization Training of PLDA for Speaker Verification

Autor:	He, Liang, Chen, Xianhong, Xu, Can, Liu, Jia
Rok vydání:	2018
Předmět:	Computer Science - Sound Computer Science - Machine Learning Electrical Engineering and Systems Science - Audio and Speech Processing
Druh dokumentu:	Working Paper
Popis:	Most current state-of-the-art text-independent speaker verification systems take probabilistic linear discriminant analysis (PLDA) as their backend classifiers. The parameters of PLDA 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.
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/1808.08344 Zobrazit plný text záznamu View this record from Arxiv