The DKU-MSXF Speaker Verification System for the VoxCeleb Speaker Recognition Challenge 2023
Abstract
This paper is the system description of the DKU-MSXF System for the track1, track2 and track3 of the VoxCeleb Speaker Recognition Challenge 2023 (VoxSRC-23). For Track 1, we utilize a network structure based on ResNet for training. By constructing a cross-age QMF training set, we achieve a substantial improvement in system performance. For Track 2, we inherite the pre-trained model from Track 1 and conducte mixed training by incorporating the VoxBlink-clean dataset. In comparison to Track 1, the models incorporating VoxBlink-clean data exhibit a performance improvement by more than 10% relatively. For Track3, the semi-supervised domain adaptation task, a novel pseudo-labeling method based on triple thresholds and sub-center purification is adopted to make domain adaptation. The final submission achieves mDCF of 0.1243 in task1, mDCF of 0.1165 in Track 2 and EER of 4.952% in Track 3.
Cite
@article{arxiv.2308.08766,
title = {The DKU-MSXF Speaker Verification System for the VoxCeleb Speaker Recognition Challenge 2023},
author = {Ze Li and Yuke Lin and Xiaoyi Qin and Ning Jiang and Guoqing Zhao and Ming Li},
journal= {arXiv preprint arXiv:2308.08766},
year = {2023}
}
Comments
arXiv admin note: text overlap with arXiv:2210.05092