ISCA Archive FFSVC 2022
ISCA Archive FFSVC 2022

Cross-Domain ArcFace:Learnging Robust Speaker Representation Under the Far-Field Speaker Verification

Yuke Lin, Xiaoyi Qin, Ming Li

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.


doi: 10.21437/FFSVC.2022-2

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}
}