The Cocktail Party Problem: Speech/Data Signal Separation Comparison between Backpropagation and SONN

Part of Advances in Neural Information Processing Systems 2 (NIPS 1989)

Bibtex Metadata Paper

Authors

John Kassebaum, Manoel Tenorio, Christoph Schaefers

Abstract

This work introduces a new method called Self Organizing Neural Network (SONN) algorithm and compares its performance with Back Propagation in a signal separation application. The problem is to separate two signals; a modem data signal and a male speech signal, added and transmitted through a 4 khz channel. The signals are sam(cid:173) pled at 8 khz, and using supervised learning, an attempt is made to reconstruct them. The SONN is an algorithm that constructs its own network topology during training, which is shown to be much smaller than the BP network, faster to trained, and free from the trial-and(cid:173) error network design that characterize BP.