Query Expansion System for the VoxCeleb Speaker Recognition Challenge 2020
Sound
2020-11-06 v1 Computation and Language
Audio and Speech Processing
Abstract
In this report, we describe our submission to the VoxCeleb Speaker Recognition Challenge (VoxSRC) 2020. Two approaches are adopted. One is to apply query expansion on speaker verification, which shows significant progress compared to baseline in the study. Another is to use Kaldi extract x-vector and to combine its Probabilistic Linear Discriminant Analysis (PLDA) score with ResNet score.
Keywords
Cite
@article{arxiv.2011.02882,
title = {Query Expansion System for the VoxCeleb Speaker Recognition Challenge 2020},
author = {Yu-Sen Cheng and Chun-Liang Shih and Tien-Hong Lo and Wen-Ting Tseng and Berlin Chen},
journal= {arXiv preprint arXiv:2011.02882},
year = {2020}
}