General Information
    • ISSN: 1793-8201 (Print), 2972-4511 (Online)
    • Abbreviated Title: Int. J. Comput. Theory Eng.
    • Frequency: Quarterly
    • DOI: 10.7763/IJCTE
    • Editor-in-Chief: Prof. Mehmet Sahinoglu
    • Associate Editor-in-Chief: Assoc. Prof. Alberto Arteta, Assoc. Prof. Engin Maşazade
    • Managing Editor: Ms. Mia Hu
    • Abstracting/Indexing: Scopus (Since 2022), INSPEC (IET), CNKI,  Google Scholar, EBSCO, etc.
    • Average Days from Submission to Acceptance: 192 days
    • E-mail: ijcte@iacsitp.com
    • Journal Metrics:

Editor-in-chief
Prof. Mehmet Sahinoglu
Computer Science Department, Troy University, USA
I'm happy to take on the position of editor in chief of IJCTE. We encourage authors to submit papers concerning any branch of computer theory and engineering.

IJCTE 2012 Vol.5(2): 317-320 ISSN: 1793-8201
DOI: 10.7763/IJCTE.2013.V5.701

Performance Comparison of Multi-Class SVM Classification for Music Cultural Style Tagging

Sai Hseng Mao and Ei Ei Pe Myint

Abstract—In content centric music information retrieval (MIR); emotion, genre, similarity and style are well fashion in these days. Automatic classification of musical style is gaining more and more importance since it may serve as a way to structure and organize the increasingly large number of music files available on the Web. This paper presents cultural based music style classification task which is categorized three different cultural style; classical songs of Chinese, Indian and Myanmar. 1500 music pieces, 500 for each culture are employed for this work. Exclusively timbral texture feature set are extracted from audio files for training and testing. The Support Vector classifiers are applied for style classification based on cultural information. Performance of two different multiclass classification method, One-Against-One and One-Against-All (OAA) are compared as the main theme of this presentation. The experimental result show the 88.43% and 82.37% overall accuracy for three music cultural style classification. Moreover, the system achieved the highest accuracy of 89.13% in Myanmar culture using OAO support vector classifier and 87% in Myanmar culture using OAA support vector classifier respectively.

Index Terms—Music information retrieval, multi-class classification, OAO classification, OAA classification.

S. H. Mao is with the Computer University (Lashio) Myanmar (e-mail: saihsengmao2012@gmail.com).
E.-E. P. Myint is with the Department of Software Technology, Computer University (Lashio) Myanmar (e-mail: eieipemyint@gmail.com).

[PDF]

Cite: Sai Hseng Mao and Ei Ei Pe Myint, "Performance Comparison of Multi-Class SVM Classification for Music Cultural Style Tagging," International Journal of Computer Theory and Engineering vol. 5, no. 2, pp. 317-320, 2013.


Copyright © 2008-2024. International Association of Computer Science and Information Technology. All rights reserved.