English

Multi-Domain Adaptation by Self-Supervised Learning for Speaker Verification

Sound 2023-09-26 v1 Audio and Speech Processing

Abstract

In real-world applications, speaker recognition models often face various domain-mismatch challenges, leading to a significant drop in performance. Although numerous domain adaptation techniques have been developed to address this issue, almost all present methods focus on a simple configuration where the model is trained in one domain and deployed in another. However, real-world environments are often complex and may contain multiple domains, making the methods designed for one-to-one adaptation suboptimal. In our paper, we propose a self-supervised learning method to tackle this multi-domain adaptation problem. Building upon the basic self-supervised adaptation algorithm, we designed three strategies to make it suitable for multi-domain adaptation: an in-domain negative sampling strategy, a MoCo-like memory bank scheme, and a CORAL-like distribution alignment. We conducted experiments using VoxCeleb2 as the source domain dataset and CN-Celeb1 as the target multi-domain dataset. Our results demonstrate that our method clearly outperforms the basic self-supervised adaptation method, which simply treats the data of CN-Celeb1 as a single domain. Importantly, the improvement is consistent in nearly all in-domain tests and cross-domain tests, demonstrating the effectiveness of our proposed method.

Keywords

Cite

@article{arxiv.2309.14149,
  title  = {Multi-Domain Adaptation by Self-Supervised Learning for Speaker Verification},
  author = {Wan Lin and Lantian Li and Dong Wang},
  journal= {arXiv preprint arXiv:2309.14149},
  year   = {2023}
}

Comments

submitted to ICASSP 2024

R2 v1 2026-06-28T12:31:36.898Z