SVM-based sound classification based on MPEG-7 audio LLDs and related enhanced features

Chang Hong Lin; Meng Chi Tu; Yu Hau Chin; Wei Jun Liao; Cheng Shu Hsu; Szu Hsien Lin; Jia Ching Wang; Jhing Fa Wang

doi:10.1007/978-3-642-32692-9_67

SVM-based sound classification based on MPEG-7 audio LLDs and related enhanced features

Chang Hong Lin, Meng Chi Tu, Yu Hau Chin, Wei Jun Liao, Cheng Shu Hsu, Szu Hsien Lin, Jia Ching Wang, Jhing Fa Wang

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

8 Scopus citations

Abstract

In this paper, we present a support vector machine (SVM) based sound classifier using MPEG-7 audio low-level descriptors and related enhanced features. The SVM is used to construct an environmental sound classifier. As for the audio features, a feature set which includes MPEG-7 audio low-level descriptors, spectrum centroid, spectrum spread, and spectrum flatness, and two enhanced features, RSS and Legendre-based trend coefficients (LBTCs) of the spectrum power is adopted for sound classification. Experiments demonstrate the proposed system can achieve an 81.25% classification rate.

Original language	English
Title of host publication	Convergence and Hybrid Information Technology - 6th International Conference, ICHIT 2012, Proceedings
Pages	536-543
Number of pages	8
DOIs	https://doi.org/10.1007/978-3-642-32692-9_67
State	Published - 2012
Event	6th International Conference on Convergence and Hybrid Information Technology, ICHIT 2012 - Daejeon, Korea, Republic of Duration: 23 Aug 2012 → 25 Aug 2012

Publication series

Name	Communications in Computer and Information Science
Volume	310 CCIS
ISSN (Print)	1865-0929

Conference

Conference	6th International Conference on Convergence and Hybrid Information Technology, ICHIT 2012
Country/Territory	Korea, Republic of
City	Daejeon
Period	23/08/12 → 25/08/12

Access to Document

10.1007/978-3-642-32692-9_67

Cite this

Lin, C. H., Tu, M. C., Chin, Y. H., Liao, W. J., Hsu, C. S., Lin, S. H., Wang, J. C., & Wang, J. F. (2012). SVM-based sound classification based on MPEG-7 audio LLDs and related enhanced features. In Convergence and Hybrid Information Technology - 6th International Conference, ICHIT 2012, Proceedings (pp. 536-543). (Communications in Computer and Information Science; Vol. 310 CCIS). https://doi.org/10.1007/978-3-642-32692-9_67

@inproceedings{71d1bd86d5c842f5ba4122ec9b67a1da,

title = "SVM-based sound classification based on MPEG-7 audio LLDs and related enhanced features",

abstract = "In this paper, we present a support vector machine (SVM) based sound classifier using MPEG-7 audio low-level descriptors and related enhanced features. The SVM is used to construct an environmental sound classifier. As for the audio features, a feature set which includes MPEG-7 audio low-level descriptors, spectrum centroid, spectrum spread, and spectrum flatness, and two enhanced features, RSS and Legendre-based trend coefficients (LBTCs) of the spectrum power is adopted for sound classification. Experiments demonstrate the proposed system can achieve an 81.25% classification rate.",

author = "Lin, {Chang Hong} and Tu, {Meng Chi} and Chin, {Yu Hau} and Liao, {Wei Jun} and Hsu, {Cheng Shu} and Lin, {Szu Hsien} and Wang, {Jia Ching} and Wang, {Jhing Fa}",

year = "2012",

doi = "10.1007/978-3-642-32692-9_67",

language = "???core.languages.en_GB???",

isbn = "9783642326912",

series = "Communications in Computer and Information Science",

pages = "536--543",

booktitle = "Convergence and Hybrid Information Technology - 6th International Conference, ICHIT 2012, Proceedings",

note = "6th International Conference on Convergence and Hybrid Information Technology, ICHIT 2012 ; Conference date: 23-08-2012 Through 25-08-2012",

}

Lin, CH, Tu, MC, Chin, YH, Liao, WJ, Hsu, CS, Lin, SH, Wang, JC & Wang, JF 2012, SVM-based sound classification based on MPEG-7 audio LLDs and related enhanced features. in Convergence and Hybrid Information Technology - 6th International Conference, ICHIT 2012, Proceedings. Communications in Computer and Information Science, vol. 310 CCIS, pp. 536-543, 6th International Conference on Convergence and Hybrid Information Technology, ICHIT 2012, Daejeon, Korea, Republic of, 23/08/12. https://doi.org/10.1007/978-3-642-32692-9_67

SVM-based sound classification based on MPEG-7 audio LLDs and related enhanced features. / Lin, Chang Hong; Tu, Meng Chi; Chin, Yu Hau et al.
Convergence and Hybrid Information Technology - 6th International Conference, ICHIT 2012, Proceedings. 2012. p. 536-543 (Communications in Computer and Information Science; Vol. 310 CCIS).

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

TY - GEN

T1 - SVM-based sound classification based on MPEG-7 audio LLDs and related enhanced features

AU - Lin, Chang Hong

AU - Tu, Meng Chi

AU - Chin, Yu Hau

AU - Liao, Wei Jun

AU - Hsu, Cheng Shu

AU - Lin, Szu Hsien

AU - Wang, Jia Ching

AU - Wang, Jhing Fa

PY - 2012

Y1 - 2012

N2 - In this paper, we present a support vector machine (SVM) based sound classifier using MPEG-7 audio low-level descriptors and related enhanced features. The SVM is used to construct an environmental sound classifier. As for the audio features, a feature set which includes MPEG-7 audio low-level descriptors, spectrum centroid, spectrum spread, and spectrum flatness, and two enhanced features, RSS and Legendre-based trend coefficients (LBTCs) of the spectrum power is adopted for sound classification. Experiments demonstrate the proposed system can achieve an 81.25% classification rate.

AB - In this paper, we present a support vector machine (SVM) based sound classifier using MPEG-7 audio low-level descriptors and related enhanced features. The SVM is used to construct an environmental sound classifier. As for the audio features, a feature set which includes MPEG-7 audio low-level descriptors, spectrum centroid, spectrum spread, and spectrum flatness, and two enhanced features, RSS and Legendre-based trend coefficients (LBTCs) of the spectrum power is adopted for sound classification. Experiments demonstrate the proposed system can achieve an 81.25% classification rate.

UR - http://www.scopus.com/inward/record.url?scp=84865956167&partnerID=8YFLogxK

U2 - 10.1007/978-3-642-32692-9_67

DO - 10.1007/978-3-642-32692-9_67

M3 - 會議論文篇章

AN - SCOPUS:84865956167

SN - 9783642326912

T3 - Communications in Computer and Information Science

SP - 536

EP - 543

BT - Convergence and Hybrid Information Technology - 6th International Conference, ICHIT 2012, Proceedings

T2 - 6th International Conference on Convergence and Hybrid Information Technology, ICHIT 2012

Y2 - 23 August 2012 through 25 August 2012

ER -

SVM-based sound classification based on MPEG-7 audio LLDs and related enhanced features

Abstract

Publication series

Conference

Access to Document

Fingerprint

Cite this