High--Performance music information retrieval system for song genre classification.

Schierz, A. C. and Budka, M., 2011. High--Performance music information retrieval system for song genre classification. In: Proc. of the 19th International Symposium on Methodologies for Intelligent Systems (ISMIS'11), June 2011, Warsaw, Poland, pp. 725-733.

This is the latest version of this eprint.

Full text not available from this repository.

Official URL: http://ismis2011.ii.pw.edu.pl/index.php

DOI: 10.1007/978-3-642-21916-0_76

Abstract

With the large amounts of multimedia data produced, recorded and made available every day, there is a clear need for well--performing automatic indexing and search methods. This paper describes a music genre classification system, which was a winning solution in the Music Information Retrieval ISMIS 2011 contest. The system consisted of a powerful ensemble classifier using the Error Correcting Output Coding coupled with an original, multi--resolution clustering and iterative relabelling scheme. The two approaches used together outperformed other competing solutions by a large margin, reaching the final accuracy close to 88%.

Item Type:Conference or Workshop Item (Paper)
Series Name:Lecture Notes in Computer Science
Additional Information:19th International Symposium on Methodologies for Intelligent Systems (ISMIS'11), Warsaw University of Technology, Poland, 28-30 June 2011.
Subjects:Generalities > Computer Science and Informatics > Artificial Intelligence
Arts > Music
Group:School of Design, Engineering & Computing > Smart Technology Research Centre
ID Code:18295
Deposited By:Dr Amanda C. Schierz LEFT
Deposited On:15 Jul 2011 11:48
Last Modified:07 Mar 2013 15:47

Available Versions of this Item

Repository Staff Only -
BU Staff Only -
Help Guide - Editing Your Items in BURO