Publication
A Language Modeling Approach for the Classification of Audio Music
| Summary: | 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. |
|---|---|
| Main Authors: | Marques, Gonçalo |
| Other Authors: | Langlois, Thibault |
| Subject: | Machine Learning Music Information Retrieval |
| Year: | 2009 |
| Country: | Portugal |
| Document type: | report |
| Access type: | open access |
| Associated institution: | Universidade de Lisboa |
| Language: | English |
| Origin: | Repositório da Universidade de Lisboa |
| _version_ | 1877770615671226368 |
|---|---|
| author | Marques, Gonçalo |
| author2 | Langlois, Thibault |
| author2_role | author |
| author_facet | Marques, Gonçalo Langlois, Thibault |
| author_role | author |
| contributor_name_str_mv | Repositório Científico de Acesso Aberto da ULisboa |
| country_str | PT |
| creators_json_txt | [{\"Person.name\":\"Marques, Gonçalo\"},{\"Person.name\":\"Langlois, Thibault\"}] |
| datacite.contributors.contributor.contributorName.fl_str_mv | Repositório Científico de Acesso Aberto da ULisboa |
| datacite.creators.creator.creatorName.fl_str_mv | Marques, Gonçalo Langlois, Thibault |
| datacite.date.Accepted.fl_str_mv | 2009-03-01T00:00:00Z |
| datacite.date.available.fl_str_mv | 2009-03-19T17:49:52Z |
| datacite.date.embargoed.fl_str_mv | 2009-03-19T17:49:52Z |
| datacite.rights.fl_str_mv | http://purl.org/coar/access_right/c_abf2 |
| datacite.subjects.subject.fl_str_mv | Machine Learning Music Information Retrieval |
| datacite.titles.title.fl_str_mv | A Language Modeling Approach for the Classification of Audio Music |
| dc.contributor.none.fl_str_mv | Repositório Científico de Acesso Aberto da ULisboa |
| dc.creator.none.fl_str_mv | Marques, Gonçalo Langlois, Thibault |
| dc.date.Accepted.fl_str_mv | 2009-03-01T00:00:00Z |
| dc.date.available.fl_str_mv | 2009-03-19T17:49:52Z |
| dc.date.embargoed.fl_str_mv | 2009-03-19T17:49:52Z |
| dc.format.none.fl_str_mv | application/pdf |
| dc.identifier.none.fl_str_mv | http://hdl.handle.net/10451/14205 |
| dc.language.none.fl_str_mv | eng |
| dc.rights.none.fl_str_mv | http://purl.org/coar/access_right/c_abf2 |
| dc.subject.none.fl_str_mv | Machine Learning Music Information Retrieval |
| dc.title.fl_str_mv | A Language Modeling Approach for the Classification of Audio Music |
| dc.type.none.fl_str_mv | http://purl.org/coar/resource_type/c_93fc |
| 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. |
| dirty | 0 |
| eu_rights_str_mv | openAccess |
| format | report |
| fulltext.url.fl_str_mv | https://repositorio.ulisboa.pt/bitstreams/1beb7e2c-5013-442a-b160-697ca4af49f4/download |
| id | ul_c7edfb89a690784cd52d01638779ea50 |
| identifier.url.fl_str_mv | http://hdl.handle.net/10451/14205 |
| inst_facet_str | urn:organizationAcronym:ul{{{_:::_}}}Universidade de Lisboa |
| instacron_str | ul |
| institution | Universidade de Lisboa |
| instname_str | Universidade de Lisboa |
| language | eng |
| network_acronym_str | ul |
| network_name_str | Repositório da Universidade de Lisboa |
| oai_identifier_str | oai:repositorio.ulisboa.pt:10451/14205 |
| organization_str_mv | urn:organizationAcronym:ul |
| person_str_mv | Marques, Gonçalo Langlois, Thibault |
| publishDate | 2009 |
| repo_facet_str | urn:repositoryAcronym:ul{{{_:::_}}}Repositório da Universidade de Lisboa |
| reponame_str | Repositório da Universidade de Lisboa |
| repository_id_str | urn:repositoryAcronym:ul |
| service_str_mv | urn:repositoryAcronym:ul |
| spelling | engporThe 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.application/pdfporA Language Modeling Approach for the Classification of Audio MusicMarques, GonçaloLanglois, ThibaultHostingInstitutionOrganizationalRepositório Científico de Acesso Aberto da ULisboae-mailmailto:repositorio@ulisboa.ptrepositorio@ulisboa.ptURLhttp://repositorio.ul.pt/handle/10455/31452009-03-19T17:49:52Z2009-032009-03-01T00:00:00ZHandlehttp://hdl.handle.net/10451/14205http://purl.org/coar/access_right/c_abf2open accessMachine LearningMusic Information Retrieval115408 bytesother research producthttp://purl.org/coar/resource_type/c_93fcreporthttp://purl.org/coar/access_right/c_abf2application/pdffulltexthttps://repositorio.ulisboa.pt/bitstreams/1beb7e2c-5013-442a-b160-697ca4af49f4/download |
| spellingShingle | A Language Modeling Approach for the Classification of Audio Music Marques, Gonçalo Machine Learning Music Information Retrieval |
| status | SINGLETON |
| subject.fl_str_mv | Machine Learning Music Information Retrieval |
| title | 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_short | A Language Modeling Approach for the Classification of Audio Music |
| title_sort | A Language Modeling Approach for the Classification of Audio Music |
| topic | Machine Learning Music Information Retrieval |
| topic_facet | Machine Learning Music Information Retrieval |
| url | http://hdl.handle.net/10451/14205 |
| visible | 1 |
Funded activities
No funded projects found.