Access count of this item: 214

Files in This Item:
File Description SizeFormat 
016918611X595017.pdf595.55 kBAdobe PDFView/Open
Title: Classification of Known and Unknown Environmental Sounds Based on Self-Organized Space Using a Recurrent Neural Network
Authors: Zhang, Yang
Ogata, Tetsuya
Nishide, Shun  KAKEN_id
Takahashi, Toru
Okuno, Hiroshi G.
Author's alias: 尾形, 哲也
Keywords: Recurrent Neural Network
Sound Recognition
Neuro-dynamical System
Issue Date: 1-Oct-2011
Publisher: Brill Academic Publishers
Journal title: Advanced Robotics
Volume: 25
Issue: 17
Start page: 2127
End page: 2141
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.
Rights: © Koninklijke Brill NV, Leiden and The Robotics Society of Japan, 2011
This is not the published version. Please cite only the published version. この論文は出版社版でありません。引用の際には出版社版をご確認ご利用ください。
DOI(Published Version): 10.1163/016918611X595017
Appears in Collections:Journal Articles

Show full item record

Export to RefWorks

Export Format: 

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.