English

Koopman Regularized Deep Speech Disentanglement for Speaker Verification

Sound 2026-03-09 v1 Machine Learning

Abstract

Human speech contains both linguistic content and speaker dependent characteristics making speaker verification a key technology in identity critical applications. Modern deep learning speaker verification systems aim to learn speaker representations that are invariant to semantic content and nuisance factors such as ambient noise. However, many existing approaches depend on labelled data, textual supervision or large pretrained models as feature extractors, limiting scalability and practical deployment, raising sustainability concerns. We propose Deep Koopman Speech Disentanglement Autoencoder (DKSD-AE), a structured autoencoder that combines a novel multi-step Koopman operator learning module with instance normalization to disentangle speaker and content dynamics. Quantitative experiments across multiple datasets demonstrate that DKSD-AE achieves improved or competitive speaker verification performance compared to state-of-the-art baselines while maintaining high content EER, confirming effective disentanglement. These results are obtained with substantially fewer parameters and without textual supervision. Moreover, performance remains stable under increased evaluation scale, highlighting representation robustness and generalization. Our findings suggest that Koopman-based temporal modelling, when combined with instance normalization, provides an efficient and principled solution for speaker-focused representation learning.

Keywords

Cite

@article{arxiv.2603.05577,
  title  = {Koopman Regularized Deep Speech Disentanglement for Speaker Verification},
  author = {Nikos Chazaridis and Mohammad Belal and Rafael Mestre and Timothy J. Norman and Christine Evers},
  journal= {arXiv preprint arXiv:2603.05577},
  year   = {2026}
}

Comments

This work has been submitted to the IEEE for possible publication

R2 v1 2026-07-01T11:05:36.426Z