Classification of known and unknown environmental sounds based on self-organized space using a recurrent neural network

Yang Zhang, Tetsuya Ogata, Shun Nishide, Toru Takahashi, Hiroshi G. Okuno

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Our goal is to develop a system to learn and classify environmental sounds for robots working in the real world. In the real world, two main restrictions pertain in learning. (i) Robots have to learn using only a small amount of data in a limited time because of hardware restrictions. (ii) The system has to adapt to unknown data since it is virtually impossible to collect samples of all environmental sounds. We used a neuro-dynamical model to build a prediction and classification system. This neuro-dynamical model can self-organize sound classes into parameters by learning samples. The sound classification space, constructed by these parameters, is structured for the sound generation dynamics and obtains clusters not only for known classes, but also unknown classes. The proposed system searches on the basis of the sound classification space for classifying. In the experiment, we evaluated the accuracy of classification for both known and unknown sound classes.

Original languageEnglish
Pages (from-to)2127-2141
Number of pages15
JournalAdvanced Robotics
Volume25
Issue number17
DOIs
Publication statusPublished - 2011
Externally publishedYes

Fingerprint

Recurrent neural networks
Acoustic waves
Robots
Hardware

Keywords

  • neuro-dynamical systema
  • Recurrent neural network
  • sound recognition

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Human-Computer Interaction
  • Computer Science Applications
  • Hardware and Architecture
  • Software

Cite this

Classification of known and unknown environmental sounds based on self-organized space using a recurrent neural network. / Zhang, Yang; Ogata, Tetsuya; Nishide, Shun; Takahashi, Toru; Okuno, Hiroshi G.

In: Advanced Robotics, Vol. 25, No. 17, 2011, p. 2127-2141.

Research output: Contribution to journalArticle

@article{a34eecf8d8f847ffbbbe22e83227784d,
title = "Classification of known and unknown environmental sounds based on self-organized space using a recurrent neural network",
abstract = "Our goal is to develop a system to learn and classify environmental sounds for robots working in the real world. In the real world, two main restrictions pertain in learning. (i) Robots have to learn using only a small amount of data in a limited time because of hardware restrictions. (ii) The system has to adapt to unknown data since it is virtually impossible to collect samples of all environmental sounds. We used a neuro-dynamical model to build a prediction and classification system. This neuro-dynamical model can self-organize sound classes into parameters by learning samples. The sound classification space, constructed by these parameters, is structured for the sound generation dynamics and obtains clusters not only for known classes, but also unknown classes. The proposed system searches on the basis of the sound classification space for classifying. In the experiment, we evaluated the accuracy of classification for both known and unknown sound classes.",
keywords = "neuro-dynamical systema, Recurrent neural network, sound recognition",
author = "Yang Zhang and Tetsuya Ogata and Shun Nishide and Toru Takahashi and Okuno, {Hiroshi G.}",
year = "2011",
doi = "10.1163/016918611X595017",
language = "English",
volume = "25",
pages = "2127--2141",
journal = "Advanced Robotics",
issn = "0169-1864",
publisher = "Taylor and Francis Ltd.",
number = "17",

}

TY - JOUR

T1 - Classification of known and unknown environmental sounds based on self-organized space using a recurrent neural network

AU - Zhang, Yang

AU - Ogata, Tetsuya

AU - Nishide, Shun

AU - Takahashi, Toru

AU - Okuno, Hiroshi G.

PY - 2011

Y1 - 2011

N2 - Our goal is to develop a system to learn and classify environmental sounds for robots working in the real world. In the real world, two main restrictions pertain in learning. (i) Robots have to learn using only a small amount of data in a limited time because of hardware restrictions. (ii) The system has to adapt to unknown data since it is virtually impossible to collect samples of all environmental sounds. We used a neuro-dynamical model to build a prediction and classification system. This neuro-dynamical model can self-organize sound classes into parameters by learning samples. The sound classification space, constructed by these parameters, is structured for the sound generation dynamics and obtains clusters not only for known classes, but also unknown classes. The proposed system searches on the basis of the sound classification space for classifying. In the experiment, we evaluated the accuracy of classification for both known and unknown sound classes.

AB - Our goal is to develop a system to learn and classify environmental sounds for robots working in the real world. In the real world, two main restrictions pertain in learning. (i) Robots have to learn using only a small amount of data in a limited time because of hardware restrictions. (ii) The system has to adapt to unknown data since it is virtually impossible to collect samples of all environmental sounds. We used a neuro-dynamical model to build a prediction and classification system. This neuro-dynamical model can self-organize sound classes into parameters by learning samples. The sound classification space, constructed by these parameters, is structured for the sound generation dynamics and obtains clusters not only for known classes, but also unknown classes. The proposed system searches on the basis of the sound classification space for classifying. In the experiment, we evaluated the accuracy of classification for both known and unknown sound classes.

KW - neuro-dynamical systema

KW - Recurrent neural network

KW - sound recognition

UR - http://www.scopus.com/inward/record.url?scp=80053959146&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80053959146&partnerID=8YFLogxK

U2 - 10.1163/016918611X595017

DO - 10.1163/016918611X595017

M3 - Article

VL - 25

SP - 2127

EP - 2141

JO - Advanced Robotics

JF - Advanced Robotics

SN - 0169-1864

IS - 17

ER -