English

Large Margin Softmax Loss for Speaker Verification

Sound 2019-04-09 v1 Audio and Speech Processing

Abstract

In neural network based speaker verification, speaker embedding is expected to be discriminative between speakers while the intra-speaker distance should remain small. A variety of loss functions have been proposed to achieve this goal. In this paper, we investigate the large margin softmax loss with different configurations in speaker verification. Ring loss and minimum hyperspherical energy criterion are introduced to further improve the performance. Results on VoxCeleb show that our best system outperforms the baseline approach by 15\% in EER, and by 13\%, 33\% in minDCF08 and minDCF10, respectively.

Keywords

Cite

@article{arxiv.1904.03479,
  title  = {Large Margin Softmax Loss for Speaker Verification},
  author = {Yi Liu and Liang He and Jia Liu},
  journal= {arXiv preprint arXiv:1904.03479},
  year   = {2019}
}

Comments

submitted to Interspeech 2019. The code and models have been released

R2 v1 2026-06-23T08:31:36.069Z