mlsanityData to 7 Oct 2026

Large Margin Softmax Loss for Speaker Verification

arXiv 1904.03479 ↗First posted 6 Apr 2019cs.SD eess.AScited by 26

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 26 papers in the map (data through 7 Oct 2026). First posted on arXiv 6 Apr 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 10; 2022: 8; 2023: 3; 2024: 3; 2025: 0; 2026: 2.

26 papers.

Sort:

  1. 2021Fine-tuning wav2vec2 for speaker recognitioncited by 35
  2. 2021SphereFace Revived: Unifying Hyperspherical Face Recognitioncited by 23
  3. 2021AnyoneNet: Synchronized Speech and Talking Head Generation for Arbitrary Personcited by 17
  4. 2022Domain Agnostic Few-shot Learning for Speaker Verificationcited by 4
  5. 2022Data-Efficient Learning via Minimizing Hyperspherical Energycited by 4
  6. 2023Pairwise Similarity Learning is SimPLEcited by 4
  7. 2021Contrastive Separative Coding for Self-supervised Representation Learningcited by 3
  8. 2021Real Additive Margin Softmax for Speaker Verificationcited by 3
  9. 2022The SpeakIn Speaker Verification System for Far-Field Speaker Verification Challenge 2022cited by 3
  10. 2023Experimenting with Additive Margins for Contrastive Self-Supervised Speaker Verificationcited by 3
  11. 2024Additive Margin in Contrastive Self-Supervised Frameworks to Learn Discriminative Speaker Representationscited by 3
  12. 2021Tune-In: Training Under Negative Environments with Interference for Attention Networks Simulating Cocktail Party Effectcited by 2
14 more
  1. 2021Dynamic Multi-scale Convolution for Dialect Identificationcited by 2
  2. 2021SpeechNAS: Towards Better Trade-off between Latency and Accuracy for Large-Scale Speaker Verificationcited by 2
  3. 2022LMD: A Learnable Mask Network to Detect Adversarial Examples for Speaker Verificationcited by 2
  4. 2021Adaptive Margin Circle Loss for Speaker Verificationcited by 1
  5. 2022Training speaker recognition systems with limited datacited by 1
  6. 2022The ReturnZero System for VoxCeleb Speaker Recognition Challenge 2022cited by 1
  7. 2026Hyperbolic Additive Margin Softmax with Hierarchical Information for Speaker Verificationcited by 1
  8. 2021Exploring Deep Learning for Joint Audio-Visual Lip Biometricscited by 0
  9. 2022Privacy-Preserving Speech Representation Learning using Vector Quantizationcited by 0
  10. 2022The SpeakIn System Description for CNSRC2022cited by 0
  11. 2023Interpretable Spectrum Transformation Attacks to Speaker Recognitioncited by 0
  12. 2024Cosine Scoring with Uncertainty for Neural Speaker Embeddingcited by 0
  13. 2024Memory-Efficient Training for Deep Speaker Embedding Learning in Speaker Verificationcited by 0
  14. 2026Quality Adaptive Angular Margin Learning for Respiratory Sound Classificationcited by 0