# Pushing the limits of self-supervised speaker verification using regularized distillation framework

arXiv: https://arxiv.org/abs/2211.04168 · HTML: https://mlsanity.com/paper/2211.04168/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Nov 2022.

## Built on by (most cited first, 15 of 15)

- [3D-Speaker: A Large-Scale Multi-Device, Multi-Distance, and Multi-Dialect Corpus for Speech Representation Disentanglement](https://mlsanity.com/paper/2306.15354/) (2023)
- [What Do Self-Supervised Speech and Speaker Models Learn? New Findings From a Cross Model Layer-Wise Analysis](https://mlsanity.com/paper/2401.17632/) (2024)
- [Self-Distillation Prototypes Network: Learning Robust Speaker Representations without Supervision](https://mlsanity.com/paper/2406.11169/) (2024)
- [Towards Supervised Performance on Speaker Verification with Self-Supervised Learning by Leveraging Large-Scale ASR Models](https://mlsanity.com/paper/2406.02285/) (2024)
- [Self-Supervised Frameworks for Speaker Verification via Bootstrapped Positive Sampling](https://mlsanity.com/paper/2501.17772/) (2025)
- [Self-Supervised Embeddings for Detecting Individual Symptoms of Depression](https://mlsanity.com/paper/2406.17229/) (2024)
- [Investigation of Speaker Representation for Target-Speaker Speech Processing](https://mlsanity.com/paper/2410.11243/) (2024)
- [Self-supervised Reflective Learning through Self-distillation and Online Clustering for Speaker Representation Learning](https://mlsanity.com/paper/2401.01473/) (2024)
- [JOOCI: a Framework for Learning Comprehensive Speech Representations](https://mlsanity.com/paper/2410.11086/) (2024)
- [Pushing the Frontiers of Self-Distillation Prototypes Network with Dimension Regularization and Score Normalization](https://mlsanity.com/paper/2505.13826/) (2025)
- [SSPS: Self-Supervised Positive Sampling for Robust Self-Supervised Speaker Verification](https://mlsanity.com/paper/2505.14561/) (2025)
- [VoxAging: Continuously Tracking Speaker Aging with a Large-Scale Longitudinal Dataset in English and Mandarin](https://mlsanity.com/paper/2505.21445/) (2025)
- [Self-Distillation Prototypes Network: Learning Robust Speaker Representations without Supervision](https://mlsanity.com/paper/2308.02774/) (2023)
- [Self-Supervised Learning for Speaker Recognition: A study and review](https://mlsanity.com/paper/2602.10829/) (2026)
- [Do Speech Tokens Leak Voiceprints? Speaker Inversion Attacks Against End-to-End Speech Language Models](https://mlsanity.com/paper/2607.16870/) (2026)

## Abstract (arXiv)

Training robust speaker verification systems without speaker labels has long been a challenging task. Previous studies observed a large performance gap between self-supervised and fully supervised methods. In this paper, we apply a non-contrastive self-supervised learning framework called DIstillation with NO labels (DINO) and propose two regularization terms applied to embeddings in DINO. One regularization term guarantees the diversity of the embeddings, while the other regularization term decorrelates the variables of each embedding. The effectiveness of various data augmentation techniques are explored, on both time and frequency domain. A range of experiments conducted on the VoxCeleb datasets demonstrate the superiority of the regularized DINO framework in speaker verification. Our method achieves the state-of-the-art speaker verification performance under a single-stage self-supervised setting on VoxCeleb. Code has been made publicly available at https://github.com/alibaba-damo-academy/3D-Speaker.