Paper Info
Title
Combining Time-Delayed Decorrelation And Ica: Towards Solving The Cocktail Party Problem
Abstract
We present methods to separate blindly mixed signals recorded in a room. The learning algorithm is based on the information maximization in a single layer neural network. We focus on the implementation of the learning algorithm and on issues that arise when separating speakers in room recordings. We used an infomax approach in a feedforward neural network implemented in the frequency domain using the polynomial filter matrix algebra technique. Fast convergence speed was achieved by using a time-delayed decorrelation method as a preprocessing step. Under minimum-phase mixing conditions this preprocessing step was sufficient for the separation of signals. These methods successfully separated a recorded voice with music in the background (cocktail party problem). Finally, we discuss problems that arise in real world recordings and their potential solutions.
Year
DOI
Venue
1998
10.1109/ICASSP.1998.675498
PROCEEDINGS OF THE 1998 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING, VOLS 1-6
Keywords
Field
DocType
feedforward neural network,learning artificial intelligence,independent component analysis,feedforward neural networks,neural network,music,neural networks,frequency domain,frequency domain analysis,speech processing,polynomials,convergence,decorrelation,audio recording,matrices
Frequency domain,Feedforward neural network,Decorrelation,Pattern recognition,Cocktail party effect,Polynomial,Computer science,Artificial intelligence,Independent component analysis,Artificial neural network,Infomax
Conference
Volume
ISSN
Citations 
2
1520-6149
20
PageRank 
References 
Authors
3.03
4
4
Name
Order
Citations
PageRank
Te-Won Lee12233260.51
Ziehe, Andreas261772.50
Reinhold Orglmeister317224.04
Terrence J. Sejnowski482782135.10