Phrase based feature extraction for musical information retrieval

Author

Yanase, Takashi ; Takasu, Atsuhiro ; Adachi, Jun

Author_Institution

Dept. of Electr. Eng., Tokyo Univ., Japan

fYear

1999

fDate

1999

Firstpage

396

Lastpage

399

Abstract

This paper presents a feature extraction method for musical information retrieval. The method presented uses a feature vector consisting of frequencies of local patterns represented with n-grams, which enables efficient search from large databases. In order to improve the performance of music retrieval, we extract features at the phrase level instead of whole melody, using an automatic phrase extraction method. The presented method is applied to a small database of Japanese popular songs and its effectiveness is shown experimentally

Keywords

audio signal processing; database management systems; feature extraction; information retrieval systems; music; Japanese popular songs; automatic phrase extraction method; feature vector; large databases; local patterns; musical information retrieval; n-grams; performance; phrase based feature extraction; phrase level; Data mining; Database systems; Digital audio players; Feature extraction; Frequency; Information systems; Instruments; Music information retrieval; Spatial databases; Standards development;

fLanguage

English

Publisher

ieee

Conference_Titel

Communications, Computers and Signal Processing, 1999 IEEE Pacific Rim Conference on

Conference_Location

Victoria, BC

Print_ISBN

0-7803-5582-2

Type

conf

DOI

10.1109/PACRIM.1999.799559

Filename

799559