본문 바로가기
  • Home

The Classification of Music Styles on the Basis of Spectral Contrast Features

  • Journal of The Korea Society of Computer and Information
  • Abbr : JKSCI
  • 2017, 22(1), pp.9-14
  • DOI : 10.9708/jksci.2017.22.01.009
  • Publisher : The Korean Society Of Computer And Information
  • Research Area : Engineering > Computer Science
  • Received : December 15, 2016
  • Accepted : January 6, 2017
  • Published : January 31, 2017

Yan-bing Wang 1

1경희대학교

Accredited

ABSTRACT

In this paper, we propose that the contrast features of octave spectrum can be used to show spectral contrast features of some music clips. It shows the relative spectral distribution rather than average spectrum. From the experiment, it can be seen the method of spectral contrast features has a good performance in classification of music styles. Another comparative experiment shows that the method of spectral contrast features can better distinguish different music styles than the method of MFCC features that commonly used previously in the classification system of music styles.

Citation status

* References for papers published after 2023 are currently being built.

This paper was written with support from the National Research Foundation of Korea.