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 proceedingConference contributionpeer-review

6 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 languageEnglish
Title of host publicationConvergence and Hybrid Information Technology - 6th International Conference, ICHIT 2012, Proceedings
Pages536-543
Number of pages8
DOIs
StatePublished - 2012
Event6th International Conference on Convergence and Hybrid Information Technology, ICHIT 2012 - Daejeon, Korea, Republic of
Duration: 23 Aug 201225 Aug 2012

Publication series

NameCommunications in Computer and Information Science
Volume310 CCIS
ISSN (Print)1865-0929

Conference

Conference6th International Conference on Convergence and Hybrid Information Technology, ICHIT 2012
Country/TerritoryKorea, Republic of
CityDaejeon
Period23/08/1225/08/12

Fingerprint

Dive into the research topics of 'SVM-based sound classification based on MPEG-7 audio LLDs and related enhanced features'. Together they form a unique fingerprint.

Cite this