Automatic Music Genre Classification using Modulation Spectral Contrast Feature

Author

Lee, Chang-Hsing ; Shih, Jau-Ling ; Yu, Kun-Ming ; Su, Jung-Mau

Author_Institution

Chung Hua Univ., Hsinchu

fYear

2007

fDate

2-5 July 2007

Firstpage

204

Lastpage

207

Abstract

In this paper, we proposed a novel feature, called octave-based modulation spectral contrast (OMSC), for music genre classification. OMSC is extracted from long-term modulation spectrum analysis to represent the time-varying behavior of music signals. Experimental results have shown that OMSC outperforms MFCC and OSC. If OMSC is integrated with MFCC and OSC, the classification accuracy is 84.03% for seven music genre classification.

Keywords

audio signal processing; electronic music; feature extraction; modulation; signal classification; spectral analysis; OMSC extraction; automatic music genre classification; digital music; octave-based modulation spectrum analysis; spectral contrast feature; time-varying behavior; Cepstral analysis; Data mining; Feature extraction; Histograms; Linear discriminant analysis; Mel frequency cepstral coefficient; Multiple signal classification; Speech; Support vector machine classification; Support vector machines;

fLanguage

English

Publisher

ieee

Conference_Titel

Multimedia and Expo, 2007 IEEE International Conference on

Conference_Location

Beijing

Print_ISBN

1-4244-1016-9

Electronic_ISBN

1-4244-1017-7

Type

conf

DOI

10.1109/ICME.2007.4284622

Filename

4284622

Link To Document

https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=3195135