The reviewed record of science sign in
Pith

arxiv: 2309.00376 · v1 · pith:EQE5EWMJ · submitted 2023-09-01 · eess.AS · cs.SD

Remixing-based Unsupervised Source Separation from Scratch

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:EQE5EWMJrecord.jsonopen to challenge →

classification eess.AS cs.SD
keywords teachertrainingscratchapproachmodelmodelsseparationmethods
0
0 comments X
read the original 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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.