Presentation 2000/7/11
Self-Organizing Neural Networks for Sound Source Localization Ability
Hiromichi Nakashima, Noboru Ohnishi,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We propose a learning model of sound source localization in a non-linear motor system with self-organizing through the interaction between motion and audio-visual sensing. This ability is acquired by repeated sensing and moving. The model consists of two modules-a visual estimation module and an auditory estimation module. These modules consist of a self-organizing feature map. These two modules learne at once. The visual estimation module learns by direct inverse modeling and the auditory estimation module uses the output from the visual estimation module to learn. We conducted computer simulation experiments to investigate the validity of the proposed module. The experimental results demonstrate that sound source localization ability can be acquired without supervision for a nanlinear system and the system is robust for noize and experimental environment.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Integration of sense and motion / Motor control / Learning model / Sound source localization
Paper # NC2000-43
Date of Issue

Conference Information
Committee NC
Conference Date 2000/7/11(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Neurocomputing (NC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Self-Organizing Neural Networks for Sound Source Localization Ability
Sub Title (in English)
Keyword(1) Integration of sense and motion
Keyword(2) Motor control
Keyword(3) Learning model
Keyword(4) Sound source localization
1st Author's Name Hiromichi Nakashima
1st Author's Affiliation Department of Information Engineering()
2nd Author's Name Noboru Ohnishi
2nd Author's Affiliation Department of Information Engineering:RIKEN BMC Research Center
Date 2000/7/11
Paper # NC2000-43
Volume (vol) vol.100
Number (no) 191
Page pp.pp.-
#Pages 8
Date of Issue