Large Margin Softmax Loss For Speaker Verification

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.

Stats

• citations89
• S2 citations—
• github stars0
• HF likes0
• heat score14.66
• arxiv keyliu2019large

Related papers

• Angular Softmax Loss For End-to-end Speaker Verification (2018)11.19
• Margin Matters: Towards More Discriminative Deep Neural Network Embeddings For Speaker Recognition (2019)15.25
• Scoring Of Large-margin Embeddings For Speaker Verification: Cosine Or PLDA? (2022)9.76
• Unified Hypersphere Embedding For Speaker Recognition (2018)0.00
• A Comparison Of Metric Learning Loss Functions For End-to-end Speaker Verification (2020)6.77
• Experimenting With Additive Margins For Contrastive Self-supervised Speaker Verification (2023)4.52
• Improved Large-margin Softmax Loss For Speaker Diarisation (2019)6.34
• Challenging Margin-based Speaker Embedding Extractors By Using The Variational Information Bottleneck (2024)0.00