This paper describes the XMUSPEECH speaker recognition and diarisation systems for the VoxCeleb Speaker Recognition Challenge 2021. For track 2, we evaluate two systems including ResNet34-SE and ECAPA-TDNN. For track 4, an important part of our system is VAD module which greatly improves the performance. Our best submission on the track 4 obtained on the evaluation set DER 5.54% and JER 27.11%, while the performance on the development set is DER 2.92% and JER 20.84%.
Cite
@article{arxiv.2109.02549,
title = {XMUSPEECH System for VoxCeleb Speaker Recognition Challenge 2021},
author = {Jie Wang and Fuchuang Tong and Zhicong Chen and Lin Li and Qingyang Hong and Haodong Zhou},
journal= {arXiv preprint arXiv:2109.02549},
year = {2021}
}