# Self-Supervised Learning Based Domain Adaptation for Robust Speaker Verification

arXiv: https://arxiv.org/abs/2108.13843 · HTML: https://mlsanity.com/paper/2108.13843/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Aug 2021.

## Built on by (most cited first, 9 of 9)

- [Self-Supervised Contrastive Pre-Training For Time Series via Time-Frequency Consistency](https://mlsanity.com/paper/2206.08496/) (2022)
- [Improving Distortion Robustness of Self-supervised Speech Processing Tasks with Domain Adaptation](https://mlsanity.com/paper/2203.16104/) (2022)
- [Self-supervised learning for infant cry analysis](https://mlsanity.com/paper/2305.01578/) (2023)
- [DT-SV: A Transformer-based Time-domain Approach for Speaker Verification](https://mlsanity.com/paper/2205.13249/) (2022)
- [The Royalflush System for VoxCeleb Speaker Recognition Challenge 2022](https://mlsanity.com/paper/2209.09010/) (2022)
- [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)
- [Automatic Data Augmentation for Domain Adapted Fine-Tuning of Self-Supervised Speech Representations](https://mlsanity.com/paper/2306.00481/) (2023)
- [Feature Normalization for Fine-tuning Self-Supervised Models in Speech Enhancement](https://mlsanity.com/paper/2306.08406/) (2023)

## Abstract (arXiv)

Large performance degradation is often observed for speaker ver-ification systems when applied to a new domain dataset. Givenan unlabeled target-domain dataset, unsupervised domain adaptation(UDA) methods, which usually leverage adversarial training strate-gies, are commonly used to bridge the performance gap caused bythe domain mismatch. However, such adversarial training strategyonly uses the distribution information of target domain data and cannot ensure the performance improvement on the target domain. Inthis paper, we incorporate self-supervised learning strategy to the un-supervised domain adaptation system and proposed a self-supervisedlearning based domain adaptation approach (SSDA). Compared tothe traditional UDA method, the new SSDA training strategy canfully leverage the potential label information from target domainand adapt the speaker discrimination ability from source domainsimultaneously. We evaluated the proposed approach on the Vox-Celeb (labeled source domain) and CnCeleb (unlabeled target do-main) datasets, and the best SSDA system obtains 10.2% Equal ErrorRate (EER) on the CnCeleb dataset without using any speaker labelson CnCeleb, which also can achieve the state-of-the-art results onthis corpus.