# An iterative framework for self-supervised deep speaker representation learning

arXiv: https://arxiv.org/abs/2010.14751 · HTML: https://mlsanity.com/paper/2010.14751/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Oct 2020.

## Built on by (most cited first, 8 of 8)

- [Pushing the limits of raw waveform speaker recognition](https://mlsanity.com/paper/2203.08488/) (2022)
- [Disentangling Voice and Content with Self-Supervision for Speaker Recognition](https://mlsanity.com/paper/2310.01128/) (2023)
- [The VoxCeleb Speaker Recognition Challenge: A Retrospective](https://mlsanity.com/paper/2408.14886/) (2024)
- [Training speaker recognition systems with limited data](https://mlsanity.com/paper/2203.14688/) (2022)
- [Self-supervised Reflective Learning through Self-distillation and Online Clustering for Speaker Representation Learning](https://mlsanity.com/paper/2401.01473/) (2024)
- [Cluster-Guided Unsupervised Domain Adaptation for Deep Speaker Embedding](https://mlsanity.com/paper/2303.15944/) (2023)
- [Progressive Sub-Graph Clustering Algorithm for Semi-Supervised Domain Adaptation Speaker Verification](https://mlsanity.com/paper/2305.12703/) (2023)
- [Self-Supervised Learning for Speaker Recognition: A study and review](https://mlsanity.com/paper/2602.10829/) (2026)

## Abstract (arXiv)

In this paper, we propose an iterative framework for self-supervised speaker representation learning based on a deep neural network (DNN). The framework starts with training a self-supervision speaker embedding network by maximizing agreement between different segments within an utterance via a contrastive loss. Taking advantage of DNN's ability to learn from data with label noise, we propose to cluster the speaker embedding obtained from the previous speaker network and use the subsequent class assignments as pseudo labels to train a new DNN. Moreover, we iteratively train the speaker network with pseudo labels generated from the previous step to bootstrap the discriminative power of a DNN. Speaker verification experiments are conducted on the VoxCeleb dataset. The results show that our proposed iterative self-supervised learning framework outperformed previous works using self-supervision. The speaker network after 5 iterations obtains a 61% performance gain over the speaker embedding model trained with contrastive loss.