# Large Margin Softmax Loss for Speaker Verification

arXiv: https://arxiv.org/abs/1904.03479 · HTML: https://mlsanity.com/paper/1904.03479/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Apr 2019.

## Built on by (most cited first, 29 of 29)

- [Fine-tuning wav2vec2 for speaker recognition](https://mlsanity.com/paper/2109.15053/) (2021)
- [SphereFace Revived: Unifying Hyperspherical Face Recognition](https://mlsanity.com/paper/2109.05565/) (2021)
- [AnyoneNet: Synchronized Speech and Talking Head Generation for Arbitrary Person](https://mlsanity.com/paper/2108.04325/) (2021)
- [Domain Agnostic Few-shot Learning for Speaker Verification](https://mlsanity.com/paper/2206.13700/) (2022)
- [Data-Efficient Learning via Minimizing Hyperspherical Energy](https://mlsanity.com/paper/2206.15204/) (2022)
- [Pairwise Similarity Learning is SimPLE](https://mlsanity.com/paper/2310.09449/) (2023)
- [Contrastive Separative Coding for Self-supervised Representation Learning](https://mlsanity.com/paper/2103.00816/) (2021)
- [Real Additive Margin Softmax for Speaker Verification](https://mlsanity.com/paper/2110.09116/) (2021)
- [The SpeakIn Speaker Verification System for Far-Field Speaker Verification Challenge 2022](https://mlsanity.com/paper/2209.11625/) (2022)
- [Experimenting with Additive Margins for Contrastive Self-Supervised Speaker Verification](https://mlsanity.com/paper/2306.03664/) (2023)
- [Additive Margin in Contrastive Self-Supervised Frameworks to Learn Discriminative Speaker Representations](https://mlsanity.com/paper/2404.14913/) (2024)
- [Tune-In: Training Under Negative Environments with Interference for Attention Networks Simulating Cocktail Party Effect](https://mlsanity.com/paper/2103.01461/) (2021)
- [Dynamic Multi-scale Convolution for Dialect Identification](https://mlsanity.com/paper/2108.07787/) (2021)
- [SpeechNAS: Towards Better Trade-off between Latency and Accuracy for Large-Scale Speaker Verification](https://mlsanity.com/paper/2109.08839/) (2021)
- [Training speaker recognition systems with limited data](https://mlsanity.com/paper/2203.14688/) (2022)
- [LMD: A Learnable Mask Network to Detect Adversarial Examples for Speaker Verification](https://mlsanity.com/paper/2211.00825/) (2022)
- [Adaptive Margin Circle Loss for Speaker Verification](https://mlsanity.com/paper/2106.08004/) (2021)
- [The ReturnZero System for VoxCeleb Speaker Recognition Challenge 2022](https://mlsanity.com/paper/2209.10147/) (2022)
- [Label-free Knowledge Distillation with Contrastive Loss for Light-weight Speaker Recognition](https://mlsanity.com/paper/2212.03090/) (2022)
- [A Teacher-Student approach for extracting informative speaker embeddings from speech mixtures](https://mlsanity.com/paper/2306.00634/) (2023)
- [Hyperbolic Additive Margin Softmax with Hierarchical Information for Speaker Verification](https://mlsanity.com/paper/2601.19709/) (2026)
- [Exploring Deep Learning for Joint Audio-Visual Lip Biometrics](https://mlsanity.com/paper/2104.08510/) (2021)
- [Privacy-Preserving Speech Representation Learning using Vector Quantization](https://mlsanity.com/paper/2203.09518/) (2022)
- [The SpeakIn System Description for CNSRC2022](https://mlsanity.com/paper/2209.10846/) (2022)
- [Interpretable Spectrum Transformation Attacks to Speaker Recognition](https://mlsanity.com/paper/2302.10686/) (2023)
- [Geodesic interpolation of frame-wise speaker embeddings for the diarization of meeting scenarios](https://mlsanity.com/paper/2401.03963/) (2024)
- [Cosine Scoring with Uncertainty for Neural Speaker Embedding](https://mlsanity.com/paper/2403.06404/) (2024)
- [Memory-Efficient Training for Deep Speaker Embedding Learning in Speaker Verification](https://mlsanity.com/paper/2412.01195/) (2024)
- [Quality Adaptive Angular Margin Learning for Respiratory Sound Classification](https://mlsanity.com/paper/2606.11915/) (2026)

## 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.