The system of speaker verification system shows outstanding performance with the assistance of different types of loss functions with angular margin penalty, which can enforce the intra-class compactness and inter-class discrepancy. However, the power of classification may degrade largely when encountering the cross-domain problems, especially in far-field scenes. Thus, we propose a novel Cross-Domain ArcFace(CD-ArcFace) loss function. By adopting distinct margin penalty in different do-main when conducting mix-data fine-tuning, the performance of various speaker verification system can be further improved. This experiment is carried on FFSVC2022. The final score level of our fusion system for the task1 achieves 4.028% and 4.368% EER on the development set and evaluation set.
Cite as: Lin, Y., Qin, X., Li, M. (2022) Cross-Domain ArcFace:Learnging Robust Speaker Representation Under the Far-Field Speaker Verification. Proc. The 2022 Far-field Speaker Verification Challenge (FFSVC2022), 6-9, doi: 10.21437/FFSVC.2022-2
@inproceedings{lin22_ffsvc,
author={Yuke Lin and Xiaoyi Qin and Ming Li},
title={{Cross-Domain ArcFace:Learnging Robust Speaker Representation Under the Far-Field Speaker Verification}},
year=2022,
booktitle={Proc. The 2022 Far-field Speaker Verification Challenge (FFSVC2022)},
pages={6--9},
doi={10.21437/FFSVC.2022-2}
}