# Self-Supervised Speaker Verification Using Dynamic Loss-Gate and Label Correction

arXiv: https://arxiv.org/abs/2208.01928 · HTML: https://mlsanity.com/paper/2208.01928/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Aug 2022.

## Built on by (most cited first, 6 of 6)

- [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 Reflective Learning through Self-distillation and Online Clustering for Speaker Representation Learning](https://mlsanity.com/paper/2401.01473/) (2024)
- [SSPS: Self-Supervised Positive Sampling for Robust Self-Supervised Speaker Verification](https://mlsanity.com/paper/2505.14561/) (2025)
- [Self-supervised learning with diffusion-based multichannel speech enhancement for speaker verification under noisy conditions](https://mlsanity.com/paper/2307.02244/) (2023)
- [Self-Supervised Learning for Speaker Recognition: A study and review](https://mlsanity.com/paper/2602.10829/) (2026)

## Abstract (arXiv)

For self-supervised speaker verification, the quality of pseudo labels decides the upper bound of the system due to the massive unreliable labels. In this work, we propose dynamic loss-gate and label correction (DLG-LC) to alleviate the performance degradation caused by unreliable estimated labels. In DLG, we adopt Gaussian Mixture Model (GMM) to dynamically model the loss distribution and use the estimated GMM to distinguish the reliable and unreliable labels automatically. Besides, to better utilize the unreliable data instead of dropping them directly, we correct the unreliable label with model predictions. Moreover, we apply the negative-pairs-free DINO framework in our experiments for further improvement. Compared to the best-known speaker verification system with self-supervised learning, our proposed DLG-LC converges faster and achieves 11.45%, 18.35% and 15.16% relative improvement on Vox-O, Vox-E and Vox-H trials of Voxceleb1 evaluation dataset.