Adversarial Generative NMF for Single Channel Source Separation

Autor:	Ludvigsen, Martin, Grasmair, Markus
Rok vydání:	2023
Předmět:	Electrical Engineering and Systems Science - Audio and Speech Processing Computer Science - Machine Learning Mathematics - Numerical Analysis Statistics - Machine Learning 94A12 (primary) 47A52 94A08 (secondary)
Druh dokumentu:	Working Paper
Popis:	The idea of adversarial learning of regularization functionals has recently been introduced in the wider context of inverse problems. The intuition behind this method is the realization that it is not only necessary to learn the basic features that make up a class of signals one wants to represent, but also, or even more so, which features to avoid in the representation. In this paper, we will apply this approach to the problem of source separation by means of non-negative matrix factorization (NMF) and present a new method for the adversarial training of NMF bases. We show in numerical experiments, both for image and audio separation, that this leads to a clear improvement of the reconstructed signals, in particular in the case where little or no strong supervision data is available. Comment: 24 pages, 4 figures
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2305.01758 Zobrazit plný text záznamu View this record from Arxiv