This system description describes our submission system to the Third DIHARD Speech Diarization Challenge. Besides the traditional clustering based system, the innovation of our system lies in the combination of various front-end techniques to solve the diarization problem, including speech separation and target-speaker based voice activity detection (TS-VAD), combined with iterative data purification. We also adopted audio domain classification to design domain-dependent processing. Finally, we performed post processing to do system fusion and selection. Our best system achieved DERs of 11.30% in track 1 and 16.78% in track 2 on evaluation set, respectively.
@article{arxiv.2103.10661,
title = {USTC-NELSLIP System Description for DIHARD-III Challenge},
author = {Yuxuan Wang and Maokui He and Shutong Niu and Lei Sun and Tian Gao and Xin Fang and Jia Pan and Jun Du and Chin-Hui Lee},
journal= {arXiv preprint arXiv:2103.10661},
year = {2021}
}