Neural network configuration for multiple sound source location and its performance

Shinichi Sato, Takuro Sato, Atsushi Fukasawa

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

The method of estimating multiple sound source induction based on a neural network algorithm and its performance are described in this paper. An evaluation function is first defined to reflect both properties of sound propagation of spherical wave front and the uniqueness of solution. A neural network is then compared to satisfy the conditions for the above evaluation function. Locations of multiple sources are given as exciting neurons. The proposed method is evaluated and compared with the deterministic method on the Hyperbolic Method for the case of 8 sources on a square plane of 200 m × 200 m. It is found that the solutions are obtained correctly without any pseudo or dropped-out solutions. The proposed method is also applied to another case in which 54 sound sources are composed of 9 sound groups, each of which contains 6 sound sources. The proposed method is found to be effective and sufficient for practical application.

Original languageEnglish
Pages (from-to)754-760
Number of pages7
JournalIEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences
VolumeE76-A
Issue number5
Publication statusPublished - 1993 May
Externally publishedYes

Fingerprint

Acoustic waves
Neural Networks
Neural networks
Configuration
Function evaluation
Evaluation Function
Uniqueness of Solutions
Neurons
Network Algorithms
Wave Front
Sound
Neuron
Proof by induction
Propagation
Sufficient

ASJC Scopus subject areas

  • Hardware and Architecture
  • Information Systems
  • Electrical and Electronic Engineering

Cite this

Neural network configuration for multiple sound source location and its performance. / Sato, Shinichi; Sato, Takuro; Fukasawa, Atsushi.

In: IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences, Vol. E76-A, No. 5, 05.1993, p. 754-760.

Research output: Contribution to journalArticle

@article{c7a18ce28b8b45ccb0c6dc8a1abcbebf,
title = "Neural network configuration for multiple sound source location and its performance",
abstract = "The method of estimating multiple sound source induction based on a neural network algorithm and its performance are described in this paper. An evaluation function is first defined to reflect both properties of sound propagation of spherical wave front and the uniqueness of solution. A neural network is then compared to satisfy the conditions for the above evaluation function. Locations of multiple sources are given as exciting neurons. The proposed method is evaluated and compared with the deterministic method on the Hyperbolic Method for the case of 8 sources on a square plane of 200 m × 200 m. It is found that the solutions are obtained correctly without any pseudo or dropped-out solutions. The proposed method is also applied to another case in which 54 sound sources are composed of 9 sound groups, each of which contains 6 sound sources. The proposed method is found to be effective and sufficient for practical application.",
author = "Shinichi Sato and Takuro Sato and Atsushi Fukasawa",
year = "1993",
month = "5",
language = "English",
volume = "E76-A",
pages = "754--760",
journal = "IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences",
issn = "0916-8508",
publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",
number = "5",

}

TY - JOUR

T1 - Neural network configuration for multiple sound source location and its performance

AU - Sato, Shinichi

AU - Sato, Takuro

AU - Fukasawa, Atsushi

PY - 1993/5

Y1 - 1993/5

N2 - The method of estimating multiple sound source induction based on a neural network algorithm and its performance are described in this paper. An evaluation function is first defined to reflect both properties of sound propagation of spherical wave front and the uniqueness of solution. A neural network is then compared to satisfy the conditions for the above evaluation function. Locations of multiple sources are given as exciting neurons. The proposed method is evaluated and compared with the deterministic method on the Hyperbolic Method for the case of 8 sources on a square plane of 200 m × 200 m. It is found that the solutions are obtained correctly without any pseudo or dropped-out solutions. The proposed method is also applied to another case in which 54 sound sources are composed of 9 sound groups, each of which contains 6 sound sources. The proposed method is found to be effective and sufficient for practical application.

AB - The method of estimating multiple sound source induction based on a neural network algorithm and its performance are described in this paper. An evaluation function is first defined to reflect both properties of sound propagation of spherical wave front and the uniqueness of solution. A neural network is then compared to satisfy the conditions for the above evaluation function. Locations of multiple sources are given as exciting neurons. The proposed method is evaluated and compared with the deterministic method on the Hyperbolic Method for the case of 8 sources on a square plane of 200 m × 200 m. It is found that the solutions are obtained correctly without any pseudo or dropped-out solutions. The proposed method is also applied to another case in which 54 sound sources are composed of 9 sound groups, each of which contains 6 sound sources. The proposed method is found to be effective and sufficient for practical application.

UR - http://www.scopus.com/inward/record.url?scp=0027596671&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0027596671&partnerID=8YFLogxK

M3 - Article

VL - E76-A

SP - 754

EP - 760

JO - IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences

JF - IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences

SN - 0916-8508

IS - 5

ER -