# Additive Margin in Contrastive Self-Supervised Frameworks to Learn Discriminative Speaker Representations

arXiv: https://arxiv.org/abs/2404.14913 · HTML: https://mlsanity.com/paper/2404.14913/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 21 references that are in the map.
- First posted on arXiv 23 Apr 2024.

## Builds on (most cited first, 14 of 14)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [CosFace: Large Margin Cosine Loss for Deep Face Recognition](https://mlsanity.com/paper/1801.09414/) (2018)
- [Self-Supervised Speech Representation Learning: A Review](https://mlsanity.com/paper/2205.10643/) (2022)
- [In defence of metric learning for speaker recognition](https://mlsanity.com/paper/2003.11982/) (2020)
- [Utterance-level Aggregation For Speaker Recognition In The Wild](https://mlsanity.com/paper/1902.10107/) (2019)
- [Self-supervised Text-independent Speaker Verification using Prototypical Momentum Contrastive Learning](https://mlsanity.com/paper/2012.07178/) (2020)
- [Large Margin Softmax Loss for Speaker Verification](https://mlsanity.com/paper/1904.03479/) (2019)
- [Augmentation adversarial training for self-supervised speaker recognition](https://mlsanity.com/paper/2007.12085/) (2020)
- [Delving into VoxCeleb: environment invariant speaker recognition](https://mlsanity.com/paper/1910.11238/) (2019)
- [Self-supervised speaker embeddings](https://mlsanity.com/paper/1904.03486/) (2019)
- [Label-Efficient Self-Supervised Speaker Verification With Information Maximization and Contrastive Learning](https://mlsanity.com/paper/2207.05506/) (2022)
- [Non-Contrastive Self-supervised Learning for Utterance-Level Information Extraction from Speech](https://mlsanity.com/paper/2208.05445/) (2022)
- [Learning Speaker Embedding from Text-to-Speech](https://mlsanity.com/paper/2010.11221/) (2020)
- [Experimenting with Additive Margins for Contrastive Self-Supervised Speaker Verification](https://mlsanity.com/paper/2306.03664/) (2023)

## Built on by (most cited first, 3 of 3)

- [Self-Supervised Frameworks for Speaker Verification via Bootstrapped Positive Sampling](https://mlsanity.com/paper/2501.17772/) (2025)
- [SSPS: Self-Supervised Positive Sampling for Robust Self-Supervised Speaker Verification](https://mlsanity.com/paper/2505.14561/) (2025)
- [Self-Supervised Learning for Speaker Recognition: A study and review](https://mlsanity.com/paper/2602.10829/) (2026)

## Abstract (arXiv)

Self-Supervised Learning (SSL) frameworks became the standard for learning robust class representations by benefiting from large unlabeled datasets. For Speaker Verification (SV), most SSL systems rely on contrastive-based loss functions. We explore different ways to improve the performance of these techniques by revisiting the NT-Xent contrastive loss. Our main contribution is the definition of the NT-Xent-AM loss and the study of the importance of Additive Margin (AM) in SimCLR and MoCo SSL methods to further separate positive from negative pairs. Despite class collisions, we show that AM enhances the compactness of same-speaker embeddings and reduces the number of false negatives and false positives on SV. Additionally, we demonstrate the effectiveness of the symmetric contrastive loss, which provides more supervision for the SSL task. Implementing these two modifications to SimCLR improves performance and results in 7.85% EER on VoxCeleb1-O, outperforming other equivalent methods.