English

Probabilistic Modelling of Signal Mixtures with Differentiable Dictionaries

Audio and Speech Processing 2022-11-29 v1 Machine Learning Sound

Abstract

We introduce a novel way to incorporate prior information into (semi-) supervised non-negative matrix factorization, which we call differentiable dictionary search. It enables general, highly flexible and principled modelling of mixtures where non-linear sources are linearly mixed. We study its behavior on an audio decomposition task, and conduct an extensive, highly controlled study of its modelling capabilities.

Keywords

Cite

@article{arxiv.2211.15439,
  title  = {Probabilistic Modelling of Signal Mixtures with Differentiable Dictionaries},
  author = {Lukáš Samuel Marták and Rainer Kelz and Gerhard Widmer},
  journal= {arXiv preprint arXiv:2211.15439},
  year   = {2022}
}

Comments

Published in the Proceedings of the 29th European Signal Processing Conference (EUSIPCO 2021), Dublin, Ireland, August 23-27, 2021 (IEEE), 441-445