Voice assignment in vocal quartets using deep learning models based on pitch salience

This paper deals with the automatic transcription of four-part, a cappella singing, audio performances. In particular, we exploit an existing, deep-learning based, multiple F0 estimation method and complement it with two neural network architectures for voice assignment (VA) in order to create a mus...

Descripción completa

Detalles Bibliográficos
Autores: Cuesta, Helena, Gómez Gutiérrez, Emilia, 1975-
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2022
País:España
Institución: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:10230/55358
Acceso en línea:http://hdl.handle.net/10230/55358
http://dx.doi.org/10.5334/tismir.121
Access Level:acceso abierto
Palabra clave:voice assignment
multi-pitch estimation
music information retrieval
vocal quartets
polyphonic vocal music
deep learning
id ES_7d83e89bde28cdda88b485abe6a29fdd
oai_identifier_str oai:recercat.cat:10230/55358
network_acronym_str ES
network_name_str España
repository_id_str
spelling Voice assignment in vocal quartets using deep learning models based on pitch salienceCuesta, HelenaGómez Gutiérrez, Emilia, 1975-voice assignmentmulti-pitch estimationmusic information retrievalvocal quartetspolyphonic vocal musicdeep learningThis paper deals with the automatic transcription of four-part, a cappella singing, audio performances. In particular, we exploit an existing, deep-learning based, multiple F0 estimation method and complement it with two neural network architectures for voice assignment (VA) in order to create a music transcription system that converts an input audio mixture into four pitch contours. To train our VA models, we create a novel synthetic dataset by collecting 5381 choral music scores from public-domain music archives, which we make publicly available for further research. We compare the performance of the proposed VA models on different types of input data, as well as to a hidden Markov model-based baseline system. In addition, we assess the generalization capabilities of these models on audio recordings with differing pitch distributions and vocal music styles. Our experiments show that the two proposed models, a CNN and a ConvLSTM, have very similar performance, and both of them outperform the baseline HMM-based system. We also observe a high confusion rate between the alto and tenor voice parts, which commonly have overlapping pitch ranges, while the bass voice has the highest scores in all evaluated scenarios.This work is partially supported by the European Commission under the TROMPA project (H2020 770376), the Spanish Ministry of Science and Innovation under the Musical AI project (PID2019-111403GB-I00), and by AGAUR (Generalitat de Catalunya) through an FI Predoctoral Grant (2018FI-B01015).Ubiquity Press202320232022info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfapplication/pdfhttp://hdl.handle.net/10230/55358http://dx.doi.org/10.5334/tismir.121reponame:Recercat. Dipósit de la Recerca de Catalunyainstname:Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)InglésTransactions of the International Society for Music Information Retrieval. 2022;5(1):99-112.https://github.com/helenacuesta/voas-vocal-quartetshttps://doi.org/10.5334/tismir.121.s1info:eu-repo/grantAgreement/EC/H2020/770376info:eu-repo/grantAgreement/ES/2PE/PID2019-111403GB-I00© 2022 The Author(s). This is an open-access article distributed under the terms of the Creative Commons Attribution 4.0 International License (CC-BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. See http://creativecommons.org/licenses/by/4.0/.http://creativecommons.org/licenses/by/4.0/info:eu-repo/semantics/openAccessoai:recercat.cat:10230/553582026-05-29T05:05:01Z
dc.title.none.fl_str_mv Voice assignment in vocal quartets using deep learning models based on pitch salience
title Voice assignment in vocal quartets using deep learning models based on pitch salience
spellingShingle Voice assignment in vocal quartets using deep learning models based on pitch salience
Cuesta, Helena
voice assignment
multi-pitch estimation
music information retrieval
vocal quartets
polyphonic vocal music
deep learning
title_short Voice assignment in vocal quartets using deep learning models based on pitch salience
title_full Voice assignment in vocal quartets using deep learning models based on pitch salience
title_fullStr Voice assignment in vocal quartets using deep learning models based on pitch salience
title_full_unstemmed Voice assignment in vocal quartets using deep learning models based on pitch salience
title_sort Voice assignment in vocal quartets using deep learning models based on pitch salience
dc.creator.none.fl_str_mv Cuesta, Helena
Gómez Gutiérrez, Emilia, 1975-
author Cuesta, Helena
author_facet Cuesta, Helena
Gómez Gutiérrez, Emilia, 1975-
author_role author
author2 Gómez Gutiérrez, Emilia, 1975-
author2_role author
dc.subject.none.fl_str_mv voice assignment
multi-pitch estimation
music information retrieval
vocal quartets
polyphonic vocal music
deep learning
topic voice assignment
multi-pitch estimation
music information retrieval
vocal quartets
polyphonic vocal music
deep learning
description This paper deals with the automatic transcription of four-part, a cappella singing, audio performances. In particular, we exploit an existing, deep-learning based, multiple F0 estimation method and complement it with two neural network architectures for voice assignment (VA) in order to create a music transcription system that converts an input audio mixture into four pitch contours. To train our VA models, we create a novel synthetic dataset by collecting 5381 choral music scores from public-domain music archives, which we make publicly available for further research. We compare the performance of the proposed VA models on different types of input data, as well as to a hidden Markov model-based baseline system. In addition, we assess the generalization capabilities of these models on audio recordings with differing pitch distributions and vocal music styles. Our experiments show that the two proposed models, a CNN and a ConvLSTM, have very similar performance, and both of them outperform the baseline HMM-based system. We also observe a high confusion rate between the alto and tenor voice parts, which commonly have overlapping pitch ranges, while the bass voice has the highest scores in all evaluated scenarios.
publishDate 2022
dc.date.none.fl_str_mv 2022
2023
2023
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/10230/55358
http://dx.doi.org/10.5334/tismir.121
url http://hdl.handle.net/10230/55358
http://dx.doi.org/10.5334/tismir.121
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv Transactions of the International Society for Music Information Retrieval. 2022;5(1):99-112.
https://github.com/helenacuesta/voas-vocal-quartets
https://doi.org/10.5334/tismir.121.s1
info:eu-repo/grantAgreement/EC/H2020/770376
info:eu-repo/grantAgreement/ES/2PE/PID2019-111403GB-I00
dc.rights.none.fl_str_mv http://creativecommons.org/licenses/by/4.0/
info:eu-repo/semantics/openAccess
rights_invalid_str_mv http://creativecommons.org/licenses/by/4.0/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv Ubiquity Press
publisher.none.fl_str_mv Ubiquity Press
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_ 1869411669622390784
score 15,811543