Feature extraction and recognition of wall impact noise

Zeng Xiangyang; Wang Qiang; Wang Lu; Lu Chenxiang

Feature extraction and recognition of wall impact noise

Zeng Xiangyang, Wang Qiang, Wang Lu, Lu Chenxiang

School of Marine Science and Technology

Northwestern Polytechnical University Xian

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

Abstract

Recognition of the impact noises emitted by electrical-drill or hammer is significant in such applications as building sound event monitoring system. The methods based on spectral features have been proved to have poor performance, therefore, in this paper a novel temporal feature has been proposed considering the similarity and volatility in frequency domain and the difference in time domain between various types of noises. When using measured data to testify the performance, it can be found that the recognition accuracy of the temporal features is better than that of the popular spectral features such as MFCC and the feature is noise robust.

Original language	English
State	Published - 2017
Event	24th International Congress on Sound and Vibration, ICSV 2017 - London, United Kingdom Duration: 23 Jul 2017 → 27 Jul 2017

Conference

Conference	24th International Congress on Sound and Vibration, ICSV 2017
Country/Territory	United Kingdom
City	London
Period	23/07/17 → 27/07/17

Keywords

Acoustic signal recognition
Feature extraction
Wall impact noise

Cite this

@conference{636ed7b61c7a4a6ea8d63c2a5b4d23ec,

title = "Feature extraction and recognition of wall impact noise",

abstract = "Recognition of the impact noises emitted by electrical-drill or hammer is significant in such applications as building sound event monitoring system. The methods based on spectral features have been proved to have poor performance, therefore, in this paper a novel temporal feature has been proposed considering the similarity and volatility in frequency domain and the difference in time domain between various types of noises. When using measured data to testify the performance, it can be found that the recognition accuracy of the temporal features is better than that of the popular spectral features such as MFCC and the feature is noise robust.",

keywords = "Acoustic signal recognition, Feature extraction, Wall impact noise",

author = "Zeng Xiangyang and Wang Qiang and Wang Lu and Lu Chenxiang",

year = "2017",

language = "英语",

note = "24th International Congress on Sound and Vibration, ICSV 2017 ; Conference date: 23-07-2017 Through 27-07-2017",

}

TY - CONF

T1 - Feature extraction and recognition of wall impact noise

AU - Xiangyang, Zeng

AU - Qiang, Wang

AU - Lu, Wang

AU - Chenxiang, Lu

PY - 2017

Y1 - 2017

N2 - Recognition of the impact noises emitted by electrical-drill or hammer is significant in such applications as building sound event monitoring system. The methods based on spectral features have been proved to have poor performance, therefore, in this paper a novel temporal feature has been proposed considering the similarity and volatility in frequency domain and the difference in time domain between various types of noises. When using measured data to testify the performance, it can be found that the recognition accuracy of the temporal features is better than that of the popular spectral features such as MFCC and the feature is noise robust.

AB - Recognition of the impact noises emitted by electrical-drill or hammer is significant in such applications as building sound event monitoring system. The methods based on spectral features have been proved to have poor performance, therefore, in this paper a novel temporal feature has been proposed considering the similarity and volatility in frequency domain and the difference in time domain between various types of noises. When using measured data to testify the performance, it can be found that the recognition accuracy of the temporal features is better than that of the popular spectral features such as MFCC and the feature is noise robust.

KW - Acoustic signal recognition

KW - Feature extraction

KW - Wall impact noise

UR - http://www.scopus.com/inward/record.url?scp=85029419573&partnerID=8YFLogxK

M3 - 论文

AN - SCOPUS:85029419573

T2 - 24th International Congress on Sound and Vibration, ICSV 2017

Y2 - 23 July 2017 through 27 July 2017

ER -

Feature extraction and recognition of wall impact noise

Abstract

Conference

Keywords

Other files and links

Fingerprint

Cite this