By Topic

An optimized feature set for music genre classification based on Support Vector Machine

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

2 Author(s)
Deepa, P.L. ; Dept. of Electron. & Commun. Eng., Mar Baselios Coll. of Eng. & Tech., Trivandrum, India ; Suresh, K.

Multimedia datas are growing at a fast rate. Music, which is one of the most popular types of online information, is a part of multimedia data and there are now hundreds of music streaming and downloading services operating on the World-Wide Web. Some of the music collections available are approaching the scale of ten million tracks and this has posed a major challenge for searching, retrieving, and organizing music content. So there is a need for automatic music classification methods for organizing these collections into different classes according to the certain information. In this work, a new effective feature extraction method is proposed for the classification of music according to the genre. Based on the calculated features, a new feature set is proposed to characterize the music content. The multi-class SVM is used for the classification purposes, which is one of the best classifying engines among the existing ones. Experiment result shows that the proposed method outperforms the existing methods implemented on the same database. A retrieval method is also proposed and its accuracy is verified using the proposed classification algorithm. The obtained accuracy indicates that the classifier and the retriever are very efficient compared to the existing ones.

Published in:

Recent Advances in Intelligent Computational Systems (RAICS), 2011 IEEE

Date of Conference:

22-24 Sept. 2011