Analysis on reliability of acoustic features for material recognition of damped impacted plates

Bingrui Zhang; Kean Chen; Yong Liang

doi:10.1109/ICIST.2013.6747852

Analysis on reliability of acoustic features for material recognition of damped impacted plates

Bingrui Zhang, Kean Chen, Yong Liang

School of Marine Science and Technology

Northwestern Polytechnical University Xian

Research output: Contribution to conference › Paper › peer-review

2 Scopus citations

Abstract

Automatic recognition of the material of struck plates was investigated. Impact sound produced by three kinds of plate materials are synthesized using the sphere-plate collision model. We extracted lots of acoustic features in view of time-domain, frequency-domain and auditory perception respectively, and exploited a three layers BP neural network as the classifier. In order to test the stability of features in the present of noise, we added white noise to synthesized sounds and obtained the results of material recognition for different signal to noise rates. The results showed that effective duration, equivalent duration and decay constant derived from temporal envelopes of sounds perform well in both precision and robustness for material recognition.

Original language	English
Pages	1641-1644
Number of pages	4
DOIs	https://doi.org/10.1109/ICIST.2013.6747852
State	Published - 2013
Event	2013 IEEE 3rd International Conference on Information Science and Technology, ICIST 2013 - Yangzhou, Jiangsu, China Duration: 23 Mar 2013 → 25 Mar 2013

Conference

Conference	2013 IEEE 3rd International Conference on Information Science and Technology, ICIST 2013
Country/Territory	China
City	Yangzhou, Jiangsu
Period	23/03/13 → 25/03/13

Access to Document

10.1109/ICIST.2013.6747852

Cite this

@conference{b2bfdf0c2a2b48ceba5405de13d0b69a,

title = "Analysis on reliability of acoustic features for material recognition of damped impacted plates",

abstract = "Automatic recognition of the material of struck plates was investigated. Impact sound produced by three kinds of plate materials are synthesized using the sphere-plate collision model. We extracted lots of acoustic features in view of time-domain, frequency-domain and auditory perception respectively, and exploited a three layers BP neural network as the classifier. In order to test the stability of features in the present of noise, we added white noise to synthesized sounds and obtained the results of material recognition for different signal to noise rates. The results showed that effective duration, equivalent duration and decay constant derived from temporal envelopes of sounds perform well in both precision and robustness for material recognition.",

author = "Bingrui Zhang and Kean Chen and Yong Liang",

year = "2013",

doi = "10.1109/ICIST.2013.6747852",

language = "英语",

pages = "1641--1644",

note = "2013 IEEE 3rd International Conference on Information Science and Technology, ICIST 2013 ; Conference date: 23-03-2013 Through 25-03-2013",

}

TY - CONF

T1 - Analysis on reliability of acoustic features for material recognition of damped impacted plates

AU - Zhang, Bingrui

AU - Chen, Kean

AU - Liang, Yong

PY - 2013

Y1 - 2013

N2 - Automatic recognition of the material of struck plates was investigated. Impact sound produced by three kinds of plate materials are synthesized using the sphere-plate collision model. We extracted lots of acoustic features in view of time-domain, frequency-domain and auditory perception respectively, and exploited a three layers BP neural network as the classifier. In order to test the stability of features in the present of noise, we added white noise to synthesized sounds and obtained the results of material recognition for different signal to noise rates. The results showed that effective duration, equivalent duration and decay constant derived from temporal envelopes of sounds perform well in both precision and robustness for material recognition.

AB - Automatic recognition of the material of struck plates was investigated. Impact sound produced by three kinds of plate materials are synthesized using the sphere-plate collision model. We extracted lots of acoustic features in view of time-domain, frequency-domain and auditory perception respectively, and exploited a three layers BP neural network as the classifier. In order to test the stability of features in the present of noise, we added white noise to synthesized sounds and obtained the results of material recognition for different signal to noise rates. The results showed that effective duration, equivalent duration and decay constant derived from temporal envelopes of sounds perform well in both precision and robustness for material recognition.

UR - http://www.scopus.com/inward/record.url?scp=84899025203&partnerID=8YFLogxK

U2 - 10.1109/ICIST.2013.6747852

DO - 10.1109/ICIST.2013.6747852

M3 - 论文

AN - SCOPUS:84899025203

SP - 1641

EP - 1644

T2 - 2013 IEEE 3rd International Conference on Information Science and Technology, ICIST 2013

Y2 - 23 March 2013 through 25 March 2013

ER -

Analysis on reliability of acoustic features for material recognition of damped impacted plates

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this