A general method to automatically generate music playlists
Autor(a) principal: | |
---|---|
Data de Publicação: | 2019 |
Tipo de documento: | Dissertação |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UFMG |
Texto Completo: | http://hdl.handle.net/1843/31794 |
Resumo: | Music is one of the most used forms of entertainment, being consumed by people all over the world. Different from other types of entertainment such as movies and plays, music is consumed in playlists, that is, several tracks are grouped together before the users listen to them. Arranging the songs in a sequence is a time-consuming task, and may require specific knowledge from the playlist creator. The objective of this work is to propose a general method to automatically generate music playlists satisfying conflicting goals. First, we will analyze users' playlists in order to understand their characteristics and music genres. Next, we will propose methods to calculate the similarity between songs using acoustic characteristics and metadata. The proposed similarity functions will be used to embed the songs in a music space, where similar songs are close to each other. Then, we will propose a general method to automatically generate a random playlist of songs connecting two anchor songs defined by the user. Based on the general method, we will construct two algorithms to generate music playlists, named ROPE and STRAW, and apply them to the constructed music spaces. With the experiments carried out, we showed the proposed algorithms are able to generate random heterogeneous music playlists with smooth transitions between songs. Finally, an online prototype is developed to allow users to test the proposed method. |
id |
UFMG_46b092788db401fea7894aac68f3e4c1 |
---|---|
oai_identifier_str |
oai:repositorio.ufmg.br:1843/31794 |
network_acronym_str |
UFMG |
network_name_str |
Repositório Institucional da UFMG |
repository_id_str |
|
spelling |
Renato Martins Assunçãohttp://lattes.cnpq.br/3575559872183767Pedro Olmo Stancioli Vaz de MeloOlga Nikolaevna GoussevskaiaFlávio Vinícius Diniz de FigueiredoNazareno Ferreira de Andradehttp://lattes.cnpq.br/9762969406382416Marcos Alves de Almeida2020-01-10T14:33:05Z2020-01-10T14:33:05Z2019-04-22http://hdl.handle.net/1843/31794Music is one of the most used forms of entertainment, being consumed by people all over the world. Different from other types of entertainment such as movies and plays, music is consumed in playlists, that is, several tracks are grouped together before the users listen to them. Arranging the songs in a sequence is a time-consuming task, and may require specific knowledge from the playlist creator. The objective of this work is to propose a general method to automatically generate music playlists satisfying conflicting goals. First, we will analyze users' playlists in order to understand their characteristics and music genres. Next, we will propose methods to calculate the similarity between songs using acoustic characteristics and metadata. The proposed similarity functions will be used to embed the songs in a music space, where similar songs are close to each other. Then, we will propose a general method to automatically generate a random playlist of songs connecting two anchor songs defined by the user. Based on the general method, we will construct two algorithms to generate music playlists, named ROPE and STRAW, and apply them to the constructed music spaces. With the experiments carried out, we showed the proposed algorithms are able to generate random heterogeneous music playlists with smooth transitions between songs. Finally, an online prototype is developed to allow users to test the proposed method.Música é uma das formas de entretenimento mais utilizadas por pessoas do mundo todo. Diferente de outros tipos de entretenimento como filmes e teatro, música é consumida por meio de playlists, isto é, várias músicas são agrupadas antes que sejam escutadas. Organizar as músicas em uma sequência é uma tarefa que demanda tempo, e pode requerer conhecimentos específicos de quem está criando as playlists. O objetivo deste trabalho é propor um método geral para gerar automaticamente playlists de música satisfazendo objetivos conflitantes. Inicialmente, nós iremos analisar playlists de música de usuários com o objetivo de entender suas características e gêneros musicais. Em seguida, iremos propor formas de calcular a similaridade entre músicas utilizando características acústicas e metadados. As funções de similaridade propostas serão utilizadas para mapear as músicas em um espaço de músicas onde músicas similares estão próximas uma das outras. Então iremos propor um método geral para gerar automaticamente uma playlist aleatória de música conectando duas músicas definidas pelo usuário. Baseado no método geral, iremos construir dois algoritmos para gerar playlists de música, chamados de ROPE e STRAW, e aplicá-los nos espaços de música construídos. Com os experimentos realizados, nós mostramos que os algoritmos propostos conseguem gerar playlists aleatórias de músicas heterogêneas com transições suaves entre as músicas. Finalmente, um protótipo online é desenvolvido para permitir usuários testarem o método proposto.CAPES - Coordenação de Aperfeiçoamento de Pessoal de Nível SuperiorengUniversidade Federal de Minas GeraisPrograma de Pós-Graduação em Ciência da ComputaçãoUFMGBrasilICX - DEPARTAMENTO DE CIÊNCIA DA COMPUTAÇÃOhttp://creativecommons.org/licenses/by-nc-nd/3.0/pt/info:eu-repo/semantics/openAccessRecuperação da InformaçãoSistemas de informação musicalLista de reprodução - músicaPlaylist GeneratorsPlaylist GeneratorsMusic EmbeddingA general method to automatically generate music playlistsUm método geral para geração automática de playlists de músicainfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisreponame:Repositório Institucional da UFMGinstname:Universidade Federal de Minas Gerais (UFMG)instacron:UFMGORIGINALDissertacaoMarcosAlmeidaFinal.pdfDissertacaoMarcosAlmeidaFinal.pdfapplication/pdf3346372https://repositorio.ufmg.br/bitstream/1843/31794/1/DissertacaoMarcosAlmeidaFinal.pdfc52358e3e157a50b47e75774c2eb91f0MD51CC-LICENSElicense_rdflicense_rdfapplication/rdf+xml; charset=utf-8811https://repositorio.ufmg.br/bitstream/1843/31794/2/license_rdfcfd6801dba008cb6adbd9838b81582abMD52LICENSElicense.txtlicense.txttext/plain; charset=utf-82119https://repositorio.ufmg.br/bitstream/1843/31794/3/license.txt34badce4be7e31e3adb4575ae96af679MD53TEXTDissertacaoMarcosAlmeidaFinal.pdf.txtDissertacaoMarcosAlmeidaFinal.pdf.txtExtracted texttext/plain157160https://repositorio.ufmg.br/bitstream/1843/31794/4/DissertacaoMarcosAlmeidaFinal.pdf.txt8f7f46025cc9b407a215115b09a35e83MD541843/317942020-01-15 17:23:19.058oai:repositorio.ufmg.br:1843/31794TElDRU7Dh0EgREUgRElTVFJJQlVJw4fDg08gTsODTy1FWENMVVNJVkEgRE8gUkVQT1NJVMOTUklPIElOU1RJVFVDSU9OQUwgREEgVUZNRwoKQ29tIGEgYXByZXNlbnRhw6fDo28gZGVzdGEgbGljZW7Dp2EsIHZvY8OqIChvIGF1dG9yIChlcykgb3UgbyB0aXR1bGFyIGRvcyBkaXJlaXRvcyBkZSBhdXRvcikgY29uY2VkZSBhbyBSZXBvc2l0w7NyaW8gSW5zdGl0dWNpb25hbCBkYSBVRk1HIChSSS1VRk1HKSBvIGRpcmVpdG8gbsOjbyBleGNsdXNpdm8gZSBpcnJldm9nw6F2ZWwgZGUgcmVwcm9kdXppciBlL291IGRpc3RyaWJ1aXIgYSBzdWEgcHVibGljYcOnw6NvIChpbmNsdWluZG8gbyByZXN1bW8pIHBvciB0b2RvIG8gbXVuZG8gbm8gZm9ybWF0byBpbXByZXNzbyBlIGVsZXRyw7RuaWNvIGUgZW0gcXVhbHF1ZXIgbWVpbywgaW5jbHVpbmRvIG9zIGZvcm1hdG9zIMOhdWRpbyBvdSB2w61kZW8uCgpWb2PDqiBkZWNsYXJhIHF1ZSBjb25oZWNlIGEgcG9sw610aWNhIGRlIGNvcHlyaWdodCBkYSBlZGl0b3JhIGRvIHNldSBkb2N1bWVudG8gZSBxdWUgY29uaGVjZSBlIGFjZWl0YSBhcyBEaXJldHJpemVzIGRvIFJJLVVGTUcuCgpWb2PDqiBjb25jb3JkYSBxdWUgbyBSZXBvc2l0w7NyaW8gSW5zdGl0dWNpb25hbCBkYSBVRk1HIHBvZGUsIHNlbSBhbHRlcmFyIG8gY29udGXDumRvLCB0cmFuc3BvciBhIHN1YSBwdWJsaWNhw6fDo28gcGFyYSBxdWFscXVlciBtZWlvIG91IGZvcm1hdG8gcGFyYSBmaW5zIGRlIHByZXNlcnZhw6fDo28uCgpWb2PDqiB0YW1iw6ltIGNvbmNvcmRhIHF1ZSBvIFJlcG9zaXTDs3JpbyBJbnN0aXR1Y2lvbmFsIGRhIFVGTUcgcG9kZSBtYW50ZXIgbWFpcyBkZSB1bWEgY8OzcGlhIGRlIHN1YSBwdWJsaWNhw6fDo28gcGFyYSBmaW5zIGRlIHNlZ3VyYW7Dp2EsIGJhY2stdXAgZSBwcmVzZXJ2YcOnw6NvLgoKVm9jw6ogZGVjbGFyYSBxdWUgYSBzdWEgcHVibGljYcOnw6NvIMOpIG9yaWdpbmFsIGUgcXVlIHZvY8OqIHRlbSBvIHBvZGVyIGRlIGNvbmNlZGVyIG9zIGRpcmVpdG9zIGNvbnRpZG9zIG5lc3RhIGxpY2Vuw6dhLiBWb2PDqiB0YW1iw6ltIGRlY2xhcmEgcXVlIG8gZGVww7NzaXRvIGRlIHN1YSBwdWJsaWNhw6fDo28gbsOjbywgcXVlIHNlamEgZGUgc2V1IGNvbmhlY2ltZW50bywgaW5mcmluZ2UgZGlyZWl0b3MgYXV0b3JhaXMgZGUgbmluZ3XDqW0uCgpDYXNvIGEgc3VhIHB1YmxpY2HDp8OjbyBjb250ZW5oYSBtYXRlcmlhbCBxdWUgdm9jw6ogbsOjbyBwb3NzdWkgYSB0aXR1bGFyaWRhZGUgZG9zIGRpcmVpdG9zIGF1dG9yYWlzLCB2b2PDqiBkZWNsYXJhIHF1ZSBvYnRldmUgYSBwZXJtaXNzw6NvIGlycmVzdHJpdGEgZG8gZGV0ZW50b3IgZG9zIGRpcmVpdG9zIGF1dG9yYWlzIHBhcmEgY29uY2VkZXIgYW8gUmVwb3NpdMOzcmlvIEluc3RpdHVjaW9uYWwgZGEgVUZNRyBvcyBkaXJlaXRvcyBhcHJlc2VudGFkb3MgbmVzdGEgbGljZW7Dp2EsIGUgcXVlIGVzc2UgbWF0ZXJpYWwgZGUgcHJvcHJpZWRhZGUgZGUgdGVyY2Vpcm9zIGVzdMOhIGNsYXJhbWVudGUgaWRlbnRpZmljYWRvIGUgcmVjb25oZWNpZG8gbm8gdGV4dG8gb3Ugbm8gY29udGXDumRvIGRhIHB1YmxpY2HDp8OjbyBvcmEgZGVwb3NpdGFkYS4KCkNBU08gQSBQVUJMSUNBw4fDg08gT1JBIERFUE9TSVRBREEgVEVOSEEgU0lETyBSRVNVTFRBRE8gREUgVU0gUEFUUk9Dw41OSU8gT1UgQVBPSU8gREUgVU1BIEFHw4pOQ0lBIERFIEZPTUVOVE8gT1UgT1VUUk8gT1JHQU5JU01PLCBWT0PDiiBERUNMQVJBIFFVRSBSRVNQRUlUT1UgVE9ET1MgRSBRVUFJU1FVRVIgRElSRUlUT1MgREUgUkVWSVPDg08gQ09NTyBUQU1Cw4lNIEFTIERFTUFJUyBPQlJJR0HDh8OVRVMgRVhJR0lEQVMgUE9SIENPTlRSQVRPIE9VIEFDT1JETy4KCk8gUmVwb3NpdMOzcmlvIEluc3RpdHVjaW9uYWwgZGEgVUZNRyBzZSBjb21wcm9tZXRlIGEgaWRlbnRpZmljYXIgY2xhcmFtZW50ZSBvIHNldSBub21lKHMpIG91IG8ocykgbm9tZXMocykgZG8ocykgZGV0ZW50b3IoZXMpIGRvcyBkaXJlaXRvcyBhdXRvcmFpcyBkYSBwdWJsaWNhw6fDo28sIGUgbsOjbyBmYXLDoSBxdWFscXVlciBhbHRlcmHDp8OjbywgYWzDqW0gZGFxdWVsYXMgY29uY2VkaWRhcyBwb3IgZXN0YSBsaWNlbsOnYS4KCg==Repositório de PublicaçõesPUBhttps://repositorio.ufmg.br/oaiopendoar:2020-01-15T20:23:19Repositório Institucional da UFMG - Universidade Federal de Minas Gerais (UFMG)false |
dc.title.pt_BR.fl_str_mv |
A general method to automatically generate music playlists |
dc.title.alternative.pt_BR.fl_str_mv |
Um método geral para geração automática de playlists de música |
title |
A general method to automatically generate music playlists |
spellingShingle |
A general method to automatically generate music playlists Marcos Alves de Almeida Playlist Generators Playlist Generators Music Embedding Recuperação da Informação Sistemas de informação musical Lista de reprodução - música |
title_short |
A general method to automatically generate music playlists |
title_full |
A general method to automatically generate music playlists |
title_fullStr |
A general method to automatically generate music playlists |
title_full_unstemmed |
A general method to automatically generate music playlists |
title_sort |
A general method to automatically generate music playlists |
author |
Marcos Alves de Almeida |
author_facet |
Marcos Alves de Almeida |
author_role |
author |
dc.contributor.advisor1.fl_str_mv |
Renato Martins Assunção |
dc.contributor.advisor1Lattes.fl_str_mv |
http://lattes.cnpq.br/3575559872183767 |
dc.contributor.advisor-co1.fl_str_mv |
Pedro Olmo Stancioli Vaz de Melo |
dc.contributor.referee1.fl_str_mv |
Olga Nikolaevna Goussevskaia |
dc.contributor.referee2.fl_str_mv |
Flávio Vinícius Diniz de Figueiredo |
dc.contributor.referee3.fl_str_mv |
Nazareno Ferreira de Andrade |
dc.contributor.authorLattes.fl_str_mv |
http://lattes.cnpq.br/9762969406382416 |
dc.contributor.author.fl_str_mv |
Marcos Alves de Almeida |
contributor_str_mv |
Renato Martins Assunção Pedro Olmo Stancioli Vaz de Melo Olga Nikolaevna Goussevskaia Flávio Vinícius Diniz de Figueiredo Nazareno Ferreira de Andrade |
dc.subject.por.fl_str_mv |
Playlist Generators Playlist Generators Music Embedding |
topic |
Playlist Generators Playlist Generators Music Embedding Recuperação da Informação Sistemas de informação musical Lista de reprodução - música |
dc.subject.other.pt_BR.fl_str_mv |
Recuperação da Informação Sistemas de informação musical Lista de reprodução - música |
description |
Music is one of the most used forms of entertainment, being consumed by people all over the world. Different from other types of entertainment such as movies and plays, music is consumed in playlists, that is, several tracks are grouped together before the users listen to them. Arranging the songs in a sequence is a time-consuming task, and may require specific knowledge from the playlist creator. The objective of this work is to propose a general method to automatically generate music playlists satisfying conflicting goals. First, we will analyze users' playlists in order to understand their characteristics and music genres. Next, we will propose methods to calculate the similarity between songs using acoustic characteristics and metadata. The proposed similarity functions will be used to embed the songs in a music space, where similar songs are close to each other. Then, we will propose a general method to automatically generate a random playlist of songs connecting two anchor songs defined by the user. Based on the general method, we will construct two algorithms to generate music playlists, named ROPE and STRAW, and apply them to the constructed music spaces. With the experiments carried out, we showed the proposed algorithms are able to generate random heterogeneous music playlists with smooth transitions between songs. Finally, an online prototype is developed to allow users to test the proposed method. |
publishDate |
2019 |
dc.date.issued.fl_str_mv |
2019-04-22 |
dc.date.accessioned.fl_str_mv |
2020-01-10T14:33:05Z |
dc.date.available.fl_str_mv |
2020-01-10T14:33:05Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/masterThesis |
format |
masterThesis |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://hdl.handle.net/1843/31794 |
url |
http://hdl.handle.net/1843/31794 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.rights.driver.fl_str_mv |
http://creativecommons.org/licenses/by-nc-nd/3.0/pt/ info:eu-repo/semantics/openAccess |
rights_invalid_str_mv |
http://creativecommons.org/licenses/by-nc-nd/3.0/pt/ |
eu_rights_str_mv |
openAccess |
dc.publisher.none.fl_str_mv |
Universidade Federal de Minas Gerais |
dc.publisher.program.fl_str_mv |
Programa de Pós-Graduação em Ciência da Computação |
dc.publisher.initials.fl_str_mv |
UFMG |
dc.publisher.country.fl_str_mv |
Brasil |
dc.publisher.department.fl_str_mv |
ICX - DEPARTAMENTO DE CIÊNCIA DA COMPUTAÇÃO |
publisher.none.fl_str_mv |
Universidade Federal de Minas Gerais |
dc.source.none.fl_str_mv |
reponame:Repositório Institucional da UFMG instname:Universidade Federal de Minas Gerais (UFMG) instacron:UFMG |
instname_str |
Universidade Federal de Minas Gerais (UFMG) |
instacron_str |
UFMG |
institution |
UFMG |
reponame_str |
Repositório Institucional da UFMG |
collection |
Repositório Institucional da UFMG |
bitstream.url.fl_str_mv |
https://repositorio.ufmg.br/bitstream/1843/31794/1/DissertacaoMarcosAlmeidaFinal.pdf https://repositorio.ufmg.br/bitstream/1843/31794/2/license_rdf https://repositorio.ufmg.br/bitstream/1843/31794/3/license.txt https://repositorio.ufmg.br/bitstream/1843/31794/4/DissertacaoMarcosAlmeidaFinal.pdf.txt |
bitstream.checksum.fl_str_mv |
c52358e3e157a50b47e75774c2eb91f0 cfd6801dba008cb6adbd9838b81582ab 34badce4be7e31e3adb4575ae96af679 8f7f46025cc9b407a215115b09a35e83 |
bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 MD5 MD5 |
repository.name.fl_str_mv |
Repositório Institucional da UFMG - Universidade Federal de Minas Gerais (UFMG) |
repository.mail.fl_str_mv |
|
_version_ |
1803589517732478976 |