Evaluation and combination of pitch estimation methods for melody extraction in symphonic classical music

The extraction of pitch information is arguably one of the most important tasks in automatic music description systems. However, previous research and evaluation datasets dealing with pitch estimation focused on relatively limited kinds of musical data. This work aims to broaden this scope by addres...

ver descrição completa

Detalhes bibliográficos
Autores: Bosch, Juan J., Marxer Piñón, Ricard, Gómez Gutiérrez, Emilia, 1975-
Formato: artículo
Estado:Versión aceptada para publicación
Fecha de publicación:2016
País:España
Recursos:Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)
Repositorio:Recercat. Dipósit de la Recerca de Catalunya
OAI Identifier:oai:recercat.cat:10230/26985
Acesso em linha:http://hdl.handle.net/10230/26985
http://dx.doi.org/10.1080/09298215.2016.1182191
Access Level:acceso abierto
Palavra-chave:Melody extraction
Music information retrieval
Music analysis
Evaluation
Symphonic music
Perception
id ES_aaf1f91efffa7047522d7e18e42fa963
oai_identifier_str oai:recercat.cat:10230/26985
network_acronym_str ES
network_name_str España
repository_id_str
spelling Evaluation and combination of pitch estimation methods for melody extraction in symphonic classical musicBosch, Juan J.Marxer Piñón, RicardGómez Gutiérrez, Emilia, 1975-Melody extractionMusic information retrievalMusic analysisEvaluationSymphonic musicPerceptionThe extraction of pitch information is arguably one of the most important tasks in automatic music description systems. However, previous research and evaluation datasets dealing with pitch estimation focused on relatively limited kinds of musical data. This work aims to broaden this scope by addressing symphonic western classical music recordings, focusing on pitch estimation for melody extraction. This material is characterized by a high number of overlapping sources, and by the fact that the melody may be played by different instrumental sections, often alternating within an excerpt. We evaluate the performance of eleven state-of-the-art pitch salience functions, multipitch estimation and melody extraction algorithms when determining the sequence of pitches corresponding to the main melody in a varied set of pieces. An important contribution of the present study is the proposed evaluation framework, including the annotation methodology, generated dataset and evaluation metrics. The results show that the assumptions made by certain methods hold better than others when dealing with this type of music signal, leading to a better performance. Additionally, we propose a simple method for combining the output of several algorithms, with promising results.This work is supported by the European Union Seventh Framework Programme FP7 / 2007-2013 through the PHENICX project (grant agreement no. 601166). This work is also (partly) supported by the Spanish Ministry of Economy and Competitiveness/nunder the Maria de Maeztu Units of Excellence Programme (MDM-2015-0502).Taylor & Francis (Routledge)20162016info:eu-repo/semantics/articleinfo:eu-repo/semantics/acceptedVersionapplication/pdfapplication/pdfhttp://hdl.handle.net/10230/26985http://dx.doi.org/10.1080/09298215.2016.1182191reponame:Recercat. Dipósit de la Recerca de Catalunyainstname:Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)InglésJournal of New Music Research. 2016;45(2):101-17http://mtg.upf.edu/download/datasets/orchsetinfo:eu-repo/grantAgreement/EC/FP7/601166© Taylor & Francis. This is an electronic version of an article published in [include the complete citation information for the final version of the article as published in the print edition of the journal]. Journal of New Music Research is available online at: www.tandfonline.com http://dx.doi.org/10.1080/09298215.2016.1182191.info:eu-repo/semantics/openAccessoai:recercat.cat:10230/269852026-05-29T05:05:01Z
dc.title.none.fl_str_mv Evaluation and combination of pitch estimation methods for melody extraction in symphonic classical music
title Evaluation and combination of pitch estimation methods for melody extraction in symphonic classical music
spellingShingle Evaluation and combination of pitch estimation methods for melody extraction in symphonic classical music
Bosch, Juan J.
Melody extraction
Music information retrieval
Music analysis
Evaluation
Symphonic music
Perception
title_short Evaluation and combination of pitch estimation methods for melody extraction in symphonic classical music
title_full Evaluation and combination of pitch estimation methods for melody extraction in symphonic classical music
title_fullStr Evaluation and combination of pitch estimation methods for melody extraction in symphonic classical music
title_full_unstemmed Evaluation and combination of pitch estimation methods for melody extraction in symphonic classical music
title_sort Evaluation and combination of pitch estimation methods for melody extraction in symphonic classical music
dc.creator.none.fl_str_mv Bosch, Juan J.
Marxer Piñón, Ricard
Gómez Gutiérrez, Emilia, 1975-
author Bosch, Juan J.
author_facet Bosch, Juan J.
Marxer Piñón, Ricard
Gómez Gutiérrez, Emilia, 1975-
author_role author
author2 Marxer Piñón, Ricard
Gómez Gutiérrez, Emilia, 1975-
author2_role author
author
dc.subject.none.fl_str_mv Melody extraction
Music information retrieval
Music analysis
Evaluation
Symphonic music
Perception
topic Melody extraction
Music information retrieval
Music analysis
Evaluation
Symphonic music
Perception
description The extraction of pitch information is arguably one of the most important tasks in automatic music description systems. However, previous research and evaluation datasets dealing with pitch estimation focused on relatively limited kinds of musical data. This work aims to broaden this scope by addressing symphonic western classical music recordings, focusing on pitch estimation for melody extraction. This material is characterized by a high number of overlapping sources, and by the fact that the melody may be played by different instrumental sections, often alternating within an excerpt. We evaluate the performance of eleven state-of-the-art pitch salience functions, multipitch estimation and melody extraction algorithms when determining the sequence of pitches corresponding to the main melody in a varied set of pieces. An important contribution of the present study is the proposed evaluation framework, including the annotation methodology, generated dataset and evaluation metrics. The results show that the assumptions made by certain methods hold better than others when dealing with this type of music signal, leading to a better performance. Additionally, we propose a simple method for combining the output of several algorithms, with promising results.
publishDate 2016
dc.date.none.fl_str_mv 2016
2016
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/acceptedVersion
format article
status_str acceptedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/10230/26985
http://dx.doi.org/10.1080/09298215.2016.1182191
url http://hdl.handle.net/10230/26985
http://dx.doi.org/10.1080/09298215.2016.1182191
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv Journal of New Music Research. 2016;45(2):101-17
http://mtg.upf.edu/download/datasets/orchset
info:eu-repo/grantAgreement/EC/FP7/601166
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv Taylor & Francis (Routledge)
publisher.none.fl_str_mv Taylor & Francis (Routledge)
dc.source.none.fl_str_mv reponame:Recercat. Dipósit de la Recerca de Catalunya
instname:Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)
instname_str Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)
reponame_str Recercat. Dipósit de la Recerca de Catalunya
collection Recercat. Dipósit de la Recerca de Catalunya
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869416225441841152
score 15,812429

Registos relacionados