Salvato in:
Dettagli Bibliografici
Autori principali: T., Pedro J. Villasana, Klejsa, Janusz, Villemoes, Lars, Hedelin, Per
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:https://arxiv.org/abs/2303.05896
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917774094237696
author T., Pedro J. Villasana
Klejsa, Janusz
Villemoes, Lars
Hedelin, Per
author_facet T., Pedro J. Villasana
Klejsa, Janusz
Villemoes, Lars
Hedelin, Per
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2303_05896
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Distribution Preserving Source Separation With Time Frequency Predictive Models
T., Pedro J. Villasana
Klejsa, Janusz
Villemoes, Lars
Hedelin, Per
Audio and Speech Processing
Machine Learning
Sound
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.
title Distribution Preserving Source Separation With Time Frequency Predictive Models
topic Audio and Speech Processing
Machine Learning
Sound
url https://arxiv.org/abs/2303.05896