English

Remixing-based Unsupervised Source Separation from Scratch

Audio and Speech Processing 2023-09-04 v1 Sound

Abstract

We propose an unsupervised approach for training separation models from scratch using RemixIT and Self-Remixing, which are recently proposed self-supervised learning methods for refining pre-trained models. They first separate mixtures with a teacher model and create pseudo-mixtures by shuffling and remixing the separated signals. A student model is then trained to separate the pseudo-mixtures using either the teacher's outputs or the initial mixtures as supervision. To refine the teacher's outputs, the teacher's weights are updated with the student's weights. While these methods originally assumed that the teacher is pre-trained, we show that they are capable of training models from scratch. We also introduce a simple remixing method to stabilize training. Experimental results demonstrate that the proposed approach outperforms mixture invariant training, which is currently the only available approach for training a monaural separation model from scratch.

Cite

@article{arxiv.2309.00376,
  title  = {Remixing-based Unsupervised Source Separation from Scratch},
  author = {Kohei Saijo and Tetsuji Ogawa},
  journal= {arXiv preprint arXiv:2309.00376},
  year   = {2023}
}

Comments

Interspeech2023, 5pages, 2figures, 2tables

R2 v1 2026-06-28T12:10:14.436Z