Presentation 1996/8/29
A Design Method of Telephone-Handsets by the Neural Network : A Method Converting Acoustic Parameters into Actual Sizes
Yoshinobu KAJIKAWA, Yasuo NOMURA, Juro OHGA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) The design in which acoustic equivalent circuit is used to design the telephone-handset is suitable for achieving given design philosophy. However, the designed acoustic parameters were not able to be converted into actual sizes. Because, theoretical formulae (relations) between the acoustic parameters in the acoustic equivalent circuit and the sizes of cavities and small holes, don't exist. Therefore, the method of modeling the above-mentioned relations by the neural network is proposed in this paper. In this method, the neural network learns the above-mentioned relations by using many pairs of acoustic parameters and actual sizes obtained by changing the sizes of cavities and small holes in telephone-handset variously. The acoustic parameters designed to achieve design philosophy given in the acoustic equivalent circuit can be converted into actual sizes according to this method. Moreover, since the scale of the neural network used to learn is small, the characteristics that learning time is short and the accuracy of the output value is high is possessed.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) neural network / acoustic parameter / acoustic equivalent circuit / telephone-handset
Paper # EA-96-32
Date of Issue

Conference Information
Committee EA
Conference Date 1996/8/29(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 Engineering Acoustics (EA)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A Design Method of Telephone-Handsets by the Neural Network : A Method Converting Acoustic Parameters into Actual Sizes
Sub Title (in English)
Keyword(1) neural network
Keyword(2) acoustic parameter
Keyword(3) acoustic equivalent circuit
Keyword(4) telephone-handset
1st Author's Name Yoshinobu KAJIKAWA
1st Author's Affiliation Department of Electronics, Faculty of Engineering, Kansai University()
2nd Author's Name Yasuo NOMURA
2nd Author's Affiliation Department of Electronics, Faculty of Engineering, Kansai University
3rd Author's Name Juro OHGA
3rd Author's Affiliation Fujitsu Laboratories Ltd.
Date 1996/8/29
Paper # EA-96-32
Volume (vol) vol.96
Number (no) 235
Page pp.pp.-
#Pages 8
Date of Issue