Polyphonic music generation using neural networks

In this project, the application of generative models for polyphonic music generation is investigated. Polyphonic music generation falls into the field of algorithmic composition, which is a field that aims to develop models to automate, partially or completely, the composition of musical pieces. Th...

Descripción completa

Detalles Bibliográficos
Autor: Loyola, Federico
Tipo de recurso: tesis de maestría
Fecha de publicación:2021
País:España
Institución:Universitat Politècnica de Catalunya (UPC)
Repositorio:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglés
OAI Identifier:oai:upcommons.upc.edu:2117/361950
Acceso en línea:https://hdl.handle.net/2117/361950
Access Level:acceso abierto
Palabra clave:Computer composition
Neural networks (Computer science)
Composició musical per ordinador
Xarxes neuronals (Informàtica)
Música -- Matemàtica
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial
id ES_e5dafd3b5d77e04b869f7b4d14fba8ef
oai_identifier_str oai:upcommons.upc.edu:2117/361950
network_acronym_str ES
network_name_str España
repository_id_str
spelling Polyphonic music generation using neural networksLoyola, FedericoComputer compositionNeural networks (Computer science)Composició musical per ordinadorXarxes neuronals (Informàtica)Música -- MatemàticaÀrees temàtiques de la UPC::Informàtica::Intel·ligència artificialIn this project, the application of generative models for polyphonic music generation is investigated. Polyphonic music generation falls into the field of algorithmic composition, which is a field that aims to develop models to automate, partially or completely, the composition of musical pieces. This process has many challenges both in terms of how to achieve the generation of musical pieces that are enjoyable and also how to perform a robust evaluation of the model to guide improvements. An extensive survey of the development of the field and the state-of-the-art is carried out. From this, two distinct generative models were chosen to apply to the problem of polyphonic music generation. The models chosen were the Restricted Boltzmann Machine and the Generative Adversarial Network. In particular, for the GAN, two architectures were used, the Deep Convolutional GAN and the Wasserstein GAN with gradient penalty. To train these models, a dataset containing over 9000 samples of classical musical pieces was used. Using a piano-roll representation of the musical pieces, these were converted into binary 2D arrays in which the vertical dimensions related to the pitch while the horizontal dimension represented the time, and note events were represented by active units. The first 16 seconds of each piece was extracted and used for training the model after applying data cleansing and preprocessing. Using implementations of these models, samples of musical pieces were generated. Based on listening tests performed by participants, the Deep Convolutional GAN achieved the best scores, with its compositions being ranked on average 4.80 on a scale from 1-5 of how enjoyable the pieces were. To perform a more objective evaluation, different musical features that describe rhythmic and melodic characteristics were extracted from the generated pieces and compared against the training dataset. These features included the implementation of the Krumhansl-Schmuckler algorithm for musical key detection and the average information rate used as an estimator of long-term musical structure. Within each set of the generated musical samples, the pairwise cross-validation using the Euclidean distance between each feature was performed. This was also performed between each set of generated samples and the features extracted from the training data, resulting in two sets of distances, the intra-set and inter-set distances. Using kernel density estimation, the probability density functions of these are obtained. Finally, the Kullback-Liebler divergence between the intra-set and inter-set distance of each feature for each generative model was calculated. The lower divergence indicates that the distributions are more similar. On average, the Restricted Boltzmann Machine obtained the lowest Kullback-Liebler divergences.Universitat Politècnica de CatalunyaNebot Castells, M. ÀngelaRomero Merino, Enrique20212021-10-2920222022-02-08master thesishttp://purl.org/coar/resource_type/c_bdccNAhttp://purl.org/coar/version/c_be7fb7dd8ff6fe43info:eu-repo/semantics/masterThesisapplication/pdfhttps://hdl.handle.net/2117/361950reponame:UPCommons. Portal del coneixement obert de la UPCinstname:Universitat Politècnica de Catalunya (UPC)Inglésengopen accesshttp://purl.org/coar/access_right/c_abf2info:eu-repo/semantics/openAccessoai:upcommons.upc.edu:2117/3619502026-05-27T15:37:01Z
dc.title.none.fl_str_mv Polyphonic music generation using neural networks
title Polyphonic music generation using neural networks
spellingShingle Polyphonic music generation using neural networks
Loyola, Federico
Computer composition
Neural networks (Computer science)
Composició musical per ordinador
Xarxes neuronals (Informàtica)
Música -- Matemàtica
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial
title_short Polyphonic music generation using neural networks
title_full Polyphonic music generation using neural networks
title_fullStr Polyphonic music generation using neural networks
title_full_unstemmed Polyphonic music generation using neural networks
title_sort Polyphonic music generation using neural networks
dc.creator.none.fl_str_mv Loyola, Federico
author Loyola, Federico
author_facet Loyola, Federico
author_role author
dc.contributor.none.fl_str_mv Nebot Castells, M. Àngela
Romero Merino, Enrique
dc.subject.none.fl_str_mv Computer composition
Neural networks (Computer science)
Composició musical per ordinador
Xarxes neuronals (Informàtica)
Música -- Matemàtica
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial
topic Computer composition
Neural networks (Computer science)
Composició musical per ordinador
Xarxes neuronals (Informàtica)
Música -- Matemàtica
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial
description In this project, the application of generative models for polyphonic music generation is investigated. Polyphonic music generation falls into the field of algorithmic composition, which is a field that aims to develop models to automate, partially or completely, the composition of musical pieces. This process has many challenges both in terms of how to achieve the generation of musical pieces that are enjoyable and also how to perform a robust evaluation of the model to guide improvements. An extensive survey of the development of the field and the state-of-the-art is carried out. From this, two distinct generative models were chosen to apply to the problem of polyphonic music generation. The models chosen were the Restricted Boltzmann Machine and the Generative Adversarial Network. In particular, for the GAN, two architectures were used, the Deep Convolutional GAN and the Wasserstein GAN with gradient penalty. To train these models, a dataset containing over 9000 samples of classical musical pieces was used. Using a piano-roll representation of the musical pieces, these were converted into binary 2D arrays in which the vertical dimensions related to the pitch while the horizontal dimension represented the time, and note events were represented by active units. The first 16 seconds of each piece was extracted and used for training the model after applying data cleansing and preprocessing. Using implementations of these models, samples of musical pieces were generated. Based on listening tests performed by participants, the Deep Convolutional GAN achieved the best scores, with its compositions being ranked on average 4.80 on a scale from 1-5 of how enjoyable the pieces were. To perform a more objective evaluation, different musical features that describe rhythmic and melodic characteristics were extracted from the generated pieces and compared against the training dataset. These features included the implementation of the Krumhansl-Schmuckler algorithm for musical key detection and the average information rate used as an estimator of long-term musical structure. Within each set of the generated musical samples, the pairwise cross-validation using the Euclidean distance between each feature was performed. This was also performed between each set of generated samples and the features extracted from the training data, resulting in two sets of distances, the intra-set and inter-set distances. Using kernel density estimation, the probability density functions of these are obtained. Finally, the Kullback-Liebler divergence between the intra-set and inter-set distance of each feature for each generative model was calculated. The lower divergence indicates that the distributions are more similar. On average, the Restricted Boltzmann Machine obtained the lowest Kullback-Liebler divergences.
publishDate 2021
dc.date.none.fl_str_mv 2021
2021-10-29
2022
2022-02-08
dc.type.none.fl_str_mv master thesis
http://purl.org/coar/resource_type/c_bdcc
NA
http://purl.org/coar/version/c_be7fb7dd8ff6fe43
dc.type.openaire.fl_str_mv info:eu-repo/semantics/masterThesis
format masterThesis
dc.identifier.none.fl_str_mv https://hdl.handle.net/2117/361950
url https://hdl.handle.net/2117/361950
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2
dc.rights.openaire.fl_str_mv info:eu-repo/semantics/openAccess
rights_invalid_str_mv open access
http://purl.org/coar/access_right/c_abf2
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Universitat Politècnica de Catalunya
publisher.none.fl_str_mv Universitat Politècnica de Catalunya
dc.source.none.fl_str_mv reponame:UPCommons. Portal del coneixement obert de la UPC
instname:Universitat Politècnica de Catalunya (UPC)
instname_str Universitat Politècnica de Catalunya (UPC)
reponame_str UPCommons. Portal del coneixement obert de la UPC
collection UPCommons. Portal del coneixement obert de la UPC
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869422716614868993
score 15.301603

Similares en LA Referencia