Opens in a new tab

AES E-Library

← Back to search

Conference Paper

Neural Network Approach to Analyze Spatial Sound

Authors: Palomäki, Kalle; Pulkki, Ville; Karjalainen, Matti

AES Conference: 16th International Conference: Spatial Sound Reproduction · Paper 16-022 · March 1999

Abstract

Self-organizing maps (SOM) and multilayer perception (MLP) neural network approaches are applied to the evaluation of spatial discrimination of real and virtual sound sources. Neural networks are trained with localization cues computed using a binaural model. The ability of the models to simulate human perception of spatial sound is analyzed.

Details

Published in
AES Conference: 16th International Conference: Spatial Sound Reproduction
Paper number
16-022
Publication date
March 6, 1999
Session subject
Spatial Sound Reproduction
Affiliation
Helsinki University of Technology, Espoo, Finland (See document for exact affiliation information.)
Type
Conference Paper