MUSIC TYPE CLASSIFICATION BY SPECTRAL CONTRAST FEATURE1

Automatic music type classification is very helpful for the management of digital music database. In this paper, Octave-based Spectral Contrast feature is proposed to represent the spectral characteristics of a music clip. It represented the relative spectral distribution instead of average spectral envelope. Experiments showed that Octave-based Spectral Contrast feature performed well in music type classification. Another comparison experiment demonstrated that Octave-based Spectral Contrast feature has a better discrimination among different music types than Mel-Frequency Cepstral Coefficients (MFCC), which is often used in previous music type classification systems. 1