Feature analysis and selection for acoustic event detection

Xiaodan Zhuang; Xi Zhou; Thomas S. Huang; Mark Hasegawa-Johnson

doi:10.1109/ICASSP.2008.4517535

Feature analysis and selection for acoustic event detection

Xiaodan Zhuang, Xi Zhou, Thomas S. Huang, Mark Hasegawa-Johnson

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Speech perceptual features, such as Mel-frequency Cepstral Coefficients (MFCC), have been widely used in acoustic event detection. However, the different spectral structures between speech and acoustic events degrade the performance of the speech feature sets. We propose quantifying the discriminative capability of each feature component according to the approximated Bayesian accuracy and deriving a discriminative feature set for acoustic event detection. Compared to MFCC, feature sets derived using the proposed approaches achieve about 30% relative accuracy improvement in acoustic event detection.

Original language	English (US)
Title of host publication	2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP
Pages	17-20
Number of pages	4
DOIs	https://doi.org/10.1109/ICASSP.2008.4517535
State	Published - 2008
Event	2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP - Las Vegas, NV, United States Duration: Mar 31 2008 → Apr 4 2008

Publication series

Name	ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
ISSN (Print)	1520-6149

Other

Other	2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP
Country/Territory	United States
City	Las Vegas, NV
Period	3/31/08 → 4/4/08

Keywords

Acoustic event detection
Bayesian Accuracy
Feature Selection
Hidden Markov Models

ASJC Scopus subject areas

Software
Signal Processing
Electrical and Electronic Engineering

Online availability

10.1109/ICASSP.2008.4517535

Library availability

Discover UIUC Full Text

Cite this

Zhuang, X., Zhou, X., Huang, T. S., & Hasegawa-Johnson, M. (2008). Feature analysis and selection for acoustic event detection. In 2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP (pp. 17-20). Article 4517535 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). https://doi.org/10.1109/ICASSP.2008.4517535

Feature analysis and selection for acoustic event detection. / Zhuang, Xiaodan; Zhou, Xi; Huang, Thomas S. et al.
2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP. 2008. p. 17-20 4517535 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Zhuang, X, Zhou, X, Huang, TS & Hasegawa-Johnson, M 2008, Feature analysis and selection for acoustic event detection. in 2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP., 4517535, ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, pp. 17-20, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP, Las Vegas, NV, United States, 3/31/08. https://doi.org/10.1109/ICASSP.2008.4517535

@inproceedings{b1d2e23326c74189a4e530ec479bb6cb,

title = "Feature analysis and selection for acoustic event detection",

abstract = "Speech perceptual features, such as Mel-frequency Cepstral Coefficients (MFCC), have been widely used in acoustic event detection. However, the different spectral structures between speech and acoustic events degrade the performance of the speech feature sets. We propose quantifying the discriminative capability of each feature component according to the approximated Bayesian accuracy and deriving a discriminative feature set for acoustic event detection. Compared to MFCC, feature sets derived using the proposed approaches achieve about 30% relative accuracy improvement in acoustic event detection.",

keywords = "Acoustic event detection, Bayesian Accuracy, Feature Selection, Hidden Markov Models",

author = "Xiaodan Zhuang and Xi Zhou and Huang, {Thomas S.} and Mark Hasegawa-Johnson",

year = "2008",

doi = "10.1109/ICASSP.2008.4517535",

language = "English (US)",

isbn = "1424414849",

series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",

pages = "17--20",

booktitle = "2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP",

note = "2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP ; Conference date: 31-03-2008 Through 04-04-2008",

}

TY - GEN

T1 - Feature analysis and selection for acoustic event detection

AU - Zhuang, Xiaodan

AU - Zhou, Xi

AU - Huang, Thomas S.

AU - Hasegawa-Johnson, Mark

PY - 2008

Y1 - 2008

N2 - Speech perceptual features, such as Mel-frequency Cepstral Coefficients (MFCC), have been widely used in acoustic event detection. However, the different spectral structures between speech and acoustic events degrade the performance of the speech feature sets. We propose quantifying the discriminative capability of each feature component according to the approximated Bayesian accuracy and deriving a discriminative feature set for acoustic event detection. Compared to MFCC, feature sets derived using the proposed approaches achieve about 30% relative accuracy improvement in acoustic event detection.

AB - Speech perceptual features, such as Mel-frequency Cepstral Coefficients (MFCC), have been widely used in acoustic event detection. However, the different spectral structures between speech and acoustic events degrade the performance of the speech feature sets. We propose quantifying the discriminative capability of each feature component according to the approximated Bayesian accuracy and deriving a discriminative feature set for acoustic event detection. Compared to MFCC, feature sets derived using the proposed approaches achieve about 30% relative accuracy improvement in acoustic event detection.

KW - Acoustic event detection

KW - Bayesian Accuracy

KW - Feature Selection

KW - Hidden Markov Models

UR - http://www.scopus.com/inward/record.url?scp=51449101221&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=51449101221&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2008.4517535

DO - 10.1109/ICASSP.2008.4517535

M3 - Conference contribution

AN - SCOPUS:51449101221

SN - 1424414849

SN - 9781424414840

T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

SP - 17

EP - 20

BT - 2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP

T2 - 2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP

Y2 - 31 March 2008 through 4 April 2008

ER -

Feature analysis and selection for acoustic event detection

Abstract

Publication series

Other

Keywords

ASJC Scopus subject areas

Online availability

Library availability

Related links

Fingerprint

Cite this