Feature set for Philippine Gong Music classification by indigenous group

Author

Valdez, Nicanor Marco P ; Guevara, Rowena Cristina L

Author_Institution

Digital Signal Process. Lab., Univ. of the Philippines Diliman, Quezon City, Philippines

fYear

2011

fDate

21-24 Nov. 2011

Firstpage

339

Lastpage

343

Abstract

In this study, the feature set which brought about the highest classification accuracy for sorting Philippine Gong Music clips by indigenous group was sought. The features reflected Timbre, Loudness, Rhythm and Melody-and-Pitch. Two classifiers were used: Support Vector Machines and Neural Networks. Sequential Feature Selection was used to optimize the feature set. The highest accuracy achieved was 90.83% when the combination of SVM, 30s clips and the full Timbre feature set (64 features) was used. K-means clustering was also done to find similarities among the gong styles of the different groups.

Keywords

music; neural nets; pattern clustering; signal classification; support vector machines; Philippine Gong music classification; classifiers; feature set; indigenous group; k-means clustering; loudness; melody-and-pitch; neural networks; rhythm; sequential feature selection; support vector machines; timbre; Accuracy; Databases; Feature extraction; Rhythm; Support vector machines; Timbre; Music Classification; Neural Network; Philippine Gong Music; Philippine Indigenous Music; SVM;

fLanguage

English

Publisher

ieee

Conference_Titel

TENCON 2011 - 2011 IEEE Region 10 Conference

Conference_Location

Bali

ISSN

2159-3442

Print_ISBN

978-1-4577-0256-3

Type

conf

DOI

10.1109/TENCON.2011.6129121

Filename

6129121