Networks for the Separation of Sources That Are Superimposed and Delayed
Abstract
We have created new networks to unmix signals which have been mixed either with time delays or via filtering. We first show that a subset of the Herault-Jutten learning rules fulfills a principle of minimum output power. We then apply this principle to extensions of the Herault-Jutten network which have delays in the feedback path. Our networks perform well on real speech and music signals that have been mixed using time delays or filtering.
Cite
Text
Platt and Faggin. "Networks for the Separation of Sources That Are Superimposed and Delayed." Neural Information Processing Systems, 1991.Markdown
[Platt and Faggin. "Networks for the Separation of Sources That Are Superimposed and Delayed." Neural Information Processing Systems, 1991.](https://mlanthology.org/neurips/1991/platt1991neurips-networks/)BibTeX
@inproceedings{platt1991neurips-networks,
title = {{Networks for the Separation of Sources That Are Superimposed and Delayed}},
author = {Platt, John C. and Faggin, Federico},
booktitle = {Neural Information Processing Systems},
year = {1991},
pages = {730-737},
url = {https://mlanthology.org/neurips/1991/platt1991neurips-networks/}
}