Towards efficient music genre classification using FastMap
Towards efficient music genre classification using FastMap
Automatic genre classification aims to correctly categorize an unknown recording with a music genre. Recent studies use the Kullback-Leibler (KL) divergence to estimate music similarity then perform classification using k-nearest neighbours (k-NN). However, this approach is not practical for large databases. We propose an efficient genre classifier that addresses the scalability problem. It uses a combination of modified FastMap algorithm and KL divergence to return the nearest neighbours then use 1- NN for classification. Our experiments showed that high accuracies are obtained while performing classification in less than 1/20 second per track.
de Leon, Franz
49495c02-9bb1-4366-b354-a49268e42c8b
Martinez, Kirk
5f711898-20fc-410e-a007-837d8c57cb18
17 September 2012
de Leon, Franz
49495c02-9bb1-4366-b354-a49268e42c8b
Martinez, Kirk
5f711898-20fc-410e-a007-837d8c57cb18
de Leon, Franz and Martinez, Kirk
(2012)
Towards efficient music genre classification using FastMap.
Towards efficient music genre classification using FastMap.
4 pp
.
Record type:
Conference or Workshop Item
(Paper)
Abstract
Automatic genre classification aims to correctly categorize an unknown recording with a music genre. Recent studies use the Kullback-Leibler (KL) divergence to estimate music similarity then perform classification using k-nearest neighbours (k-NN). However, this approach is not practical for large databases. We propose an efficient genre classifier that addresses the scalability problem. It uses a combination of modified FastMap algorithm and KL divergence to return the nearest neighbours then use 1- NN for classification. Our experiments showed that high accuracies are obtained while performing classification in less than 1/20 second per track.
Text
DAFX_2012.pdf
- Version of Record
More information
Published date: 17 September 2012
Venue - Dates:
Towards efficient music genre classification using FastMap, 2012-09-17
Organisations:
Web & Internet Science, Electronics & Computer Science
Identifiers
Local EPrints ID: 361423
URI: http://eprints.soton.ac.uk/id/eprint/361423
PURE UUID: f32f0f86-b531-4aa6-9a62-fc9ab99b48b5
Catalogue record
Date deposited: 23 Jan 2014 16:08
Last modified: 15 Mar 2024 02:53
Export record
Contributors
Author:
Franz de Leon
Author:
Kirk Martinez
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics