Presentation 2007-03-16
Construction of Recognition System using sound
Hikari KOBAYASHI, Akihiro TANAKA, Satoru KISHIDA, Toru WATANABE, Hirosi HASEGAWA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We constructed an individual identification system with three-layered neural networks. Sound signals were pre-processed by Fast Fourier Transform (FFT) and, were used as input data of three-layered neural networks. We investigated the effects of unit number of hidden and output layers on the performance of the individual identification system in the three-layered neural networks. From the results, we found that the sound signals were at least classified into 8 patterns in our neural networks. Therefore the three-layered neural networks is thought to be effective for an individual identification.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Layered Neural Network / sound / Fast Fourier Transform
Paper # NC2006-208
Date of Issue

Conference Information
Committee NC
Conference Date 2007/3/9(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) Construction of Recognition System using sound
Sub Title (in English)
Keyword(1) Layered Neural Network
Keyword(2) sound
Keyword(3) Fast Fourier Transform
1st Author's Name Hikari KOBAYASHI
1st Author's Affiliation Faculty of Engineering, Tottori University()
2nd Author's Name Akihiro TANAKA
2nd Author's Affiliation Faculty of Engineering, Tottori University
3rd Author's Name Satoru KISHIDA
3rd Author's Affiliation Faculty of Engineering, Tottori University
4th Author's Name Toru WATANABE
4th Author's Affiliation Faculty of Information Engineering, Matsue National College of Technology
5th Author's Name Hirosi HASEGAWA
5th Author's Affiliation Faculty of Engineering, Tottori University
Date 2007-03-16
Paper # NC2006-208
Volume (vol) vol.106
Number (no) 590
Page pp.pp.-
#Pages 6
Date of Issue