A machine learning approach to automatic music genre classification
Autor(a) principal: | |
---|---|
Data de Publicação: | 2008 |
Outros Autores: | , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Journal of the Brazilian Computer Society |
Texto Completo: | http://old.scielo.br/scielo.php?script=sci_arttext&pid=S0104-65002008000300002 |
Resumo: | This paper presents a non-conventional approach for the automatic music genre classification problem. The proposed approach uses multiple feature vectors and a pattern recognition ensemble approach, according to space and time decomposition schemes. Despite being music genre classification a multi-class problem, we accomplish the task using a set of binary classifiers, whose results are merged in order to produce the final music genre label (space decomposition). Music segments are also decomposed according to time segments obtained from the beginning, middle and end parts of the original music signal (time-decomposition). The final classification is obtained from the set of individual results, according to a combination procedure. Classical machine learning algorithms such as Naïve-Bayes, Decision Trees, k Nearest-Neighbors, Support Vector Machines and MultiLayer Perceptron Neural Nets are employed. Experiments were carried out on a novel dataset called Latin Music Database, which contains 3,160 music pieces categorized in 10 musical genres. Experimental results show that the proposed ensemble approach produces better results than the ones obtained from global and individual segment classifiers in most cases. Some experiments related to feature selection were also conducted, using the genetic algorithm paradigm. They show that the most important features for the classification task vary according to their origin in the music signal. |
id |
UFRGS-28_68747e5ba73039f78c2590eb768531b7 |
---|---|
oai_identifier_str |
oai:scielo:S0104-65002008000300002 |
network_acronym_str |
UFRGS-28 |
network_name_str |
Journal of the Brazilian Computer Society |
repository_id_str |
|
spelling |
A machine learning approach to automatic music genre classificationmusic genre classificationmachine learningpattern classificationfeature selectionThis paper presents a non-conventional approach for the automatic music genre classification problem. The proposed approach uses multiple feature vectors and a pattern recognition ensemble approach, according to space and time decomposition schemes. Despite being music genre classification a multi-class problem, we accomplish the task using a set of binary classifiers, whose results are merged in order to produce the final music genre label (space decomposition). Music segments are also decomposed according to time segments obtained from the beginning, middle and end parts of the original music signal (time-decomposition). The final classification is obtained from the set of individual results, according to a combination procedure. Classical machine learning algorithms such as Naïve-Bayes, Decision Trees, k Nearest-Neighbors, Support Vector Machines and MultiLayer Perceptron Neural Nets are employed. Experiments were carried out on a novel dataset called Latin Music Database, which contains 3,160 music pieces categorized in 10 musical genres. Experimental results show that the proposed ensemble approach produces better results than the ones obtained from global and individual segment classifiers in most cases. Some experiments related to feature selection were also conducted, using the genetic algorithm paradigm. They show that the most important features for the classification task vary according to their origin in the music signal.Sociedade Brasileira de Computação2008-09-01info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersiontext/htmlhttp://old.scielo.br/scielo.php?script=sci_arttext&pid=S0104-65002008000300002Journal of the Brazilian Computer Society v.14 n.3 2008reponame:Journal of the Brazilian Computer Societyinstname:Sociedade Brasileira de Computação (SBC)instacron:UFRGS10.1007/BF03192561info:eu-repo/semantics/openAccessSilla Jr.,Carlos N.Koerich,Alessandro L.Kaestner,Celso A. A.eng2008-11-03T00:00:00Zoai:scielo:S0104-65002008000300002Revistahttps://journal-bcs.springeropen.com/PUBhttps://old.scielo.br/oai/scielo-oai.phpjbcs@icmc.sc.usp.br1678-48040104-6500opendoar:2008-11-03T00:00Journal of the Brazilian Computer Society - Sociedade Brasileira de Computação (SBC)false |
dc.title.none.fl_str_mv |
A machine learning approach to automatic music genre classification |
title |
A machine learning approach to automatic music genre classification |
spellingShingle |
A machine learning approach to automatic music genre classification Silla Jr.,Carlos N. music genre classification machine learning pattern classification feature selection |
title_short |
A machine learning approach to automatic music genre classification |
title_full |
A machine learning approach to automatic music genre classification |
title_fullStr |
A machine learning approach to automatic music genre classification |
title_full_unstemmed |
A machine learning approach to automatic music genre classification |
title_sort |
A machine learning approach to automatic music genre classification |
author |
Silla Jr.,Carlos N. |
author_facet |
Silla Jr.,Carlos N. Koerich,Alessandro L. Kaestner,Celso A. A. |
author_role |
author |
author2 |
Koerich,Alessandro L. Kaestner,Celso A. A. |
author2_role |
author author |
dc.contributor.author.fl_str_mv |
Silla Jr.,Carlos N. Koerich,Alessandro L. Kaestner,Celso A. A. |
dc.subject.por.fl_str_mv |
music genre classification machine learning pattern classification feature selection |
topic |
music genre classification machine learning pattern classification feature selection |
description |
This paper presents a non-conventional approach for the automatic music genre classification problem. The proposed approach uses multiple feature vectors and a pattern recognition ensemble approach, according to space and time decomposition schemes. Despite being music genre classification a multi-class problem, we accomplish the task using a set of binary classifiers, whose results are merged in order to produce the final music genre label (space decomposition). Music segments are also decomposed according to time segments obtained from the beginning, middle and end parts of the original music signal (time-decomposition). The final classification is obtained from the set of individual results, according to a combination procedure. Classical machine learning algorithms such as Naïve-Bayes, Decision Trees, k Nearest-Neighbors, Support Vector Machines and MultiLayer Perceptron Neural Nets are employed. Experiments were carried out on a novel dataset called Latin Music Database, which contains 3,160 music pieces categorized in 10 musical genres. Experimental results show that the proposed ensemble approach produces better results than the ones obtained from global and individual segment classifiers in most cases. Some experiments related to feature selection were also conducted, using the genetic algorithm paradigm. They show that the most important features for the classification task vary according to their origin in the music signal. |
publishDate |
2008 |
dc.date.none.fl_str_mv |
2008-09-01 |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://old.scielo.br/scielo.php?script=sci_arttext&pid=S0104-65002008000300002 |
url |
http://old.scielo.br/scielo.php?script=sci_arttext&pid=S0104-65002008000300002 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
10.1007/BF03192561 |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
text/html |
dc.publisher.none.fl_str_mv |
Sociedade Brasileira de Computação |
publisher.none.fl_str_mv |
Sociedade Brasileira de Computação |
dc.source.none.fl_str_mv |
Journal of the Brazilian Computer Society v.14 n.3 2008 reponame:Journal of the Brazilian Computer Society instname:Sociedade Brasileira de Computação (SBC) instacron:UFRGS |
instname_str |
Sociedade Brasileira de Computação (SBC) |
instacron_str |
UFRGS |
institution |
UFRGS |
reponame_str |
Journal of the Brazilian Computer Society |
collection |
Journal of the Brazilian Computer Society |
repository.name.fl_str_mv |
Journal of the Brazilian Computer Society - Sociedade Brasileira de Computação (SBC) |
repository.mail.fl_str_mv |
jbcs@icmc.sc.usp.br |
_version_ |
1754734669972111360 |