DocumentCode
3134698
Title
Tune retrieval based on the similarity of melody
Author
Nakagawa, Yuka ; Nakamura, Yasuaki
Author_Institution
Dept. of Comput. Sci., Hiroshima City Univ., Japan
fYear
2002
fDate
2002
Firstpage
223
Abstract
Melody-based retrieval of music, which is one type of content-based retrieval, is proposed. Every fragment of a melody is represented as an appropriate N-dimensional vector, called a feature vector. A feature vector consists of values corresponding to intervals and rhythm of a melody. Depending on the distance between every fragment of a melody in the music database to the entered melody, k-nearest melodies can be obtained quickly using the SS-tree. A prototype system is developed to demonstrate the effectiveness of our approach.
Keywords
content-based retrieval; multimedia databases; music; tree data structures; N-dimensional vector; SS-tree; feature vector; intervals; k-nearest melodies; melody similarity; melody-based retrieval; music database; rhythm; tune retrieval; Computer science; Content based retrieval; Content management; Multimedia computing; Multimedia databases; Multimedia systems; Music information retrieval; Prototypes; Rhythm; Spatial databases;
fLanguage
English
Publisher
ieee
Conference_Titel
Web Delivering of Music, 2002. WEDELMUSIC 2002. Proceedings. Second International Conference on
Print_ISBN
0-7695-1623-8
Type
conf
DOI
10.1109/WDM.2002.1176219
Filename
1176219
Link To Document