Distribution Preserving Source Separation With Time Frequency Predictive Models
Audio and Speech Processing
2024-09-13 v1 Machine Learning
Sound
Abstract
We provide an example of a distribution preserving source separation method, which aims at addressing perceptual shortcomings of state-of-the-art methods. Our approach uses unconditioned generative models of signal sources. Reconstruction is achieved by means of mix-consistent sampling from a distribution conditioned on a realization of a mix. The separated signals follow their respective source distributions, which provides an advantage when separation results are evaluated in a listening test.
Cite
@article{arxiv.2303.05896,
title = {Distribution Preserving Source Separation With Time Frequency Predictive Models},
author = {Pedro J. Villasana T. and Janusz Klejsa and Lars Villemoes and Per Hedelin},
journal= {arXiv preprint arXiv:2303.05896},
year = {2024}
}
Comments
5 pages, 4 figures, pre-review version submitted to EUSIPCO 2023