Music style mining and classification by melody

Author

Shan, Man-Kwan ; Kuo, Fang-Fei ; Chen, Mao-Fu

Author_Institution

Dept. of Comput. Sci., Nat. Chengchi Univ., Taipei, Taiwan

Volume

1

fYear

2002

fDate

2002

Firstpage

97

Abstract

Music style is one of the features that people used to classify music. Discovery of music style is helpful for the design of a content-based music retrieval system. In this paper we investigate the mining and classification of music style by melody from a collection of MIDI music. We extract the chord from the melody and investigate the representation of extracted features and corresponding mining techniques for music classification. Experimental results show that the classification accuracy is about 70% to 84% for 2-way classification.

Keywords

content-based retrieval; data mining; electronic music; feature extraction; multimedia databases; music; pattern classification; MIDI music; chord extraction; content-based music retrieval system; extracted feature representation; melody classification; music classification; music style mining; Computer science; Content based retrieval; Data mining; Feature extraction; Hidden Markov models; Humans; Instruments; Monitoring; Multiple signal classification; Music information retrieval;

fLanguage

English

Publisher

ieee

Conference_Titel

Multimedia and Expo, 2002. ICME '02. Proceedings. 2002 IEEE International Conference on

Print_ISBN

0-7803-7304-9

Type

conf

DOI

10.1109/ICME.2002.1035727

Filename

1035727