A Language Modeling Approach for the Classification of Audio Music

Detalhes bibliográficos
Autor(a) principal: Marques, Gonçalo
Data de Publicação: 2009
Outros Autores: Langlois, Thibault
Tipo de documento: Relatório
Idioma: eng
Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
Texto Completo: http://hdl.handle.net/10451/14205
Resumo: The purpose of this paper is to present a method for the classification of musical pieces based on a language modeling approach. The method does not require any metadata and is used with raw audio format. It consists in 1) transforming music data into a sequence of symbols 2) building a model for each category by estimating n-grams from the sequences of symbols derived from the training set. The results obtained on three audio datasets show that, providing the amount of data is sufficient for estimating the transitions probabilities of the model, the approach performs very well. The performance achieved with the ISMIR 2004 Genre classification dataset is, to our knowledge, one of the best published in the literature.
id RCAP_ff4fad7ba0db7b392320384caf4a7e38
oai_identifier_str oai:repositorio.ul.pt:10451/14205
network_acronym_str RCAP
network_name_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository_id_str 7160
spelling A Language Modeling Approach for the Classification of Audio MusicMachine LearningMusic Information RetrievalThe purpose of this paper is to present a method for the classification of musical pieces based on a language modeling approach. The method does not require any metadata and is used with raw audio format. It consists in 1) transforming music data into a sequence of symbols 2) building a model for each category by estimating n-grams from the sequences of symbols derived from the training set. The results obtained on three audio datasets show that, providing the amount of data is sufficient for estimating the transitions probabilities of the model, the approach performs very well. The performance achieved with the ISMIR 2004 Genre classification dataset is, to our knowledge, one of the best published in the literature.FCTRepositório da Universidade de LisboaMarques, GonçaloLanglois, Thibault2009-03-19T17:49:52Z2009-032009-03-01T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/reportapplication/pdfhttp://hdl.handle.net/10451/14205enginfo:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2023-11-08T15:59:52Zoai:repositorio.ul.pt:10451/14205Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T21:36:02.147461Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse
dc.title.none.fl_str_mv A Language Modeling Approach for the Classification of Audio Music
title A Language Modeling Approach for the Classification of Audio Music
spellingShingle A Language Modeling Approach for the Classification of Audio Music
Marques, Gonçalo
Machine Learning
Music Information Retrieval
title_short A Language Modeling Approach for the Classification of Audio Music
title_full A Language Modeling Approach for the Classification of Audio Music
title_fullStr A Language Modeling Approach for the Classification of Audio Music
title_full_unstemmed A Language Modeling Approach for the Classification of Audio Music
title_sort A Language Modeling Approach for the Classification of Audio Music
author Marques, Gonçalo
author_facet Marques, Gonçalo
Langlois, Thibault
author_role author
author2 Langlois, Thibault
author2_role author
dc.contributor.none.fl_str_mv Repositório da Universidade de Lisboa
dc.contributor.author.fl_str_mv Marques, Gonçalo
Langlois, Thibault
dc.subject.por.fl_str_mv Machine Learning
Music Information Retrieval
topic Machine Learning
Music Information Retrieval
description The purpose of this paper is to present a method for the classification of musical pieces based on a language modeling approach. The method does not require any metadata and is used with raw audio format. It consists in 1) transforming music data into a sequence of symbols 2) building a model for each category by estimating n-grams from the sequences of symbols derived from the training set. The results obtained on three audio datasets show that, providing the amount of data is sufficient for estimating the transitions probabilities of the model, the approach performs very well. The performance achieved with the ISMIR 2004 Genre classification dataset is, to our knowledge, one of the best published in the literature.
publishDate 2009
dc.date.none.fl_str_mv 2009-03-19T17:49:52Z
2009-03
2009-03-01T00:00:00Z
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/report
format report
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://hdl.handle.net/10451/14205
url http://hdl.handle.net/10451/14205
dc.language.iso.fl_str_mv eng
language eng
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.source.none.fl_str_mv reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron:RCAAP
instname_str Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron_str RCAAP
institution RCAAP
reponame_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
collection Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository.name.fl_str_mv Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
repository.mail.fl_str_mv
_version_ 1799134258634162176

Registros relacionados