Large Margin Softmax Loss for Speaker Verification
This work addresses speaker verification for applications like security and authentication, but it is incremental as it builds on existing loss functions with minor modifications.
The paper tackled the problem of improving speaker verification by enhancing speaker embedding discriminability and reducing intra-speaker distance, resulting in a 15% improvement in EER and up to 33% in minDCF metrics on VoxCeleb.
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.