Music Emotion Recognition: The Importance of Melodic Features

Bibliographic Details
Main Author: Rocha, Bruno
Publication Date: 2013
Other Authors: Panda, Renato, Paiva, Rui Pedro
Format: Other
Language: eng
Source: Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
Download full: https://hdl.handle.net/10316/95166
Summary: We study the importance of a melodic audio (MA) feature set in music emotion recognition (MER) and compare its performance to an approach using only standard audio (SA) features. We also analyse the fusion of both types of features. Employing only SA features, the best attained performance was 46.3%, while using only MA features the best outcome was 59.1% (F- measure). A combination of SA and MA features improved results to 64%. These results might have an important impact to help break the so-called glass ceiling in MER, as most current approaches are based on SA features.
id RCAP_d9593f72572cc3fc11325a24c7b9716e
oai_identifier_str oai:estudogeral.uc.pt:10316/95166
network_acronym_str RCAP
network_name_str Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
repository_id_str https://opendoar.ac.uk/repository/7160
spelling Music Emotion Recognition: The Importance of Melodic Featuresaudiomachine learningmelodic featuresmusic emotion recognitionWe study the importance of a melodic audio (MA) feature set in music emotion recognition (MER) and compare its performance to an approach using only standard audio (SA) features. We also analyse the fusion of both types of features. Employing only SA features, the best attained performance was 46.3%, while using only MA features the best outcome was 59.1% (F- measure). A combination of SA and MA features improved results to 64%. These results might have an important impact to help break the so-called glass ceiling in MER, as most current approaches are based on SA features.This work was supported by the MOODetector project (PTDC/EIA-EIA/102185/2008), financed by the Fundação para Ciência e a Tecnologia (FCT) and Programa Operacional Temático Factores de Competitividade (COMPETE) - Portugal.2013info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/otherhttps://hdl.handle.net/10316/95166https://hdl.handle.net/10316/95166engRocha, BrunoPanda, RenatoPaiva, Rui Pedroinfo:eu-repo/semantics/openAccessreponame:Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)instname:FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologiainstacron:RCAAP2022-05-25T02:38:20Zoai:estudogeral.uc.pt:10316/95166Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireinfo@rcaap.ptopendoar:https://opendoar.ac.uk/repository/71602025-05-29T05:43:15.843695Repositórios Científicos de Acesso Aberto de Portugal (RCAAP) - FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologiafalse
dc.title.none.fl_str_mv Music Emotion Recognition: The Importance of Melodic Features
title Music Emotion Recognition: The Importance of Melodic Features
spellingShingle Music Emotion Recognition: The Importance of Melodic Features
Rocha, Bruno
audio
machine learning
melodic features
music emotion recognition
title_short Music Emotion Recognition: The Importance of Melodic Features
title_full Music Emotion Recognition: The Importance of Melodic Features
title_fullStr Music Emotion Recognition: The Importance of Melodic Features
title_full_unstemmed Music Emotion Recognition: The Importance of Melodic Features
title_sort Music Emotion Recognition: The Importance of Melodic Features
author Rocha, Bruno
author_facet Rocha, Bruno
Panda, Renato
Paiva, Rui Pedro
author_role author
author2 Panda, Renato
Paiva, Rui Pedro
author2_role author
author
dc.contributor.author.fl_str_mv Rocha, Bruno
Panda, Renato
Paiva, Rui Pedro
dc.subject.por.fl_str_mv audio
machine learning
melodic features
music emotion recognition
topic audio
machine learning
melodic features
music emotion recognition
description We study the importance of a melodic audio (MA) feature set in music emotion recognition (MER) and compare its performance to an approach using only standard audio (SA) features. We also analyse the fusion of both types of features. Employing only SA features, the best attained performance was 46.3%, while using only MA features the best outcome was 59.1% (F- measure). A combination of SA and MA features improved results to 64%. These results might have an important impact to help break the so-called glass ceiling in MER, as most current approaches are based on SA features.
publishDate 2013
dc.date.none.fl_str_mv 2013
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/other
format other
status_str publishedVersion
dc.identifier.uri.fl_str_mv https://hdl.handle.net/10316/95166
https://hdl.handle.net/10316/95166
url https://hdl.handle.net/10316/95166
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.source.none.fl_str_mv reponame:Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
instname:FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologia
instacron:RCAAP
instname_str FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologia
instacron_str RCAAP
institution RCAAP
reponame_str Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
collection Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
repository.name.fl_str_mv Repositórios Científicos de Acesso Aberto de Portugal (RCAAP) - FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologia
repository.mail.fl_str_mv info@rcaap.pt
_version_ 1833602450533122048

Similar Items