Generative Adversarial Source Separation

Generative source separation methods such as non-negative matrix factorization (NMF) or auto-encoders, rely on the assumption of an output probability density. Generative Adversarial Networks (GANs) can learn data distributions without needing a parametric assumption on the output density.

Data and Resources

Cite this as

Y.Cem Subakan, Paris Smaragdis (2025). Dataset: Generative Adversarial Source Separation. https://doi.org/10.57702/9injl0t8

DOI retrieved: January 3, 2025

Additional Info

Field Value
Created January 3, 2025
Last update January 3, 2025
Defined In https://doi.org/10.48550/arXiv.1710.10779
Author Y.Cem Subakan
More Authors
Paris Smaragdis
Homepage https://github.com/ycemsubakan/sourceseparation_misc