Automatic transcription of music using deep learning techniques
Autor(a) principal: | |
---|---|
Data de Publicação: | 2019 |
Tipo de documento: | Dissertação |
Idioma: | eng |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | http://hdl.handle.net/10400.8/4041 |
Resumo: | Music transcription is the problem of detecting notes that are being played in a musical piece. This is a difficult task that only trained people are capable of doing. Due to its difficulty, there have been a high interest in automate it. However, automatic music transcription encompasses several fields of research such as, digital signal processing, machine learning, music theory and cognition, pitch perception and psychoacoustics. All of this, makes automatic music transcription an hard problem to solve. In this work we present a novel approach of automatically transcribing piano musical pieces using deep learning techniques. We take advantage of deep learning techniques to build several classifiers, each one responsible for detecting only one musical note. In theory, this division of work would enhance the ability of each classifier to transcribe. Apart from that, we also apply two additional stages, pre-processing and post-processing, to improve the efficiency of our system. The pre-processing stage aims at improving the quality of the input data before the classification/transcription stage, while the post-processing aims at fixing errors originated during the classification stage. In the initial steps, preliminary experiments have been performed to fine tune our model, in both three stages: pre-processing, classification and post-processing. The experimental setup, using those optimized techniques and parameters, is shown and a comparison is given with other two state-of-the-art works that apply the same dataset as well as the same deep learning technique but using a different approach. By different approach we mean that a single neural network is used to detect all the musical notes rather than one neural network per each note. Our approach was able to surpass in frame-based metrics these works, while reaching close results in onset-based metrics, demonstrating the feasability of our approach. |
id |
RCAP_67b81b094b62ff59fa4039d811fb9fe6 |
---|---|
oai_identifier_str |
oai:iconline.ipleiria.pt:10400.8/4041 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
Automatic transcription of music using deep learning techniquesAutomatic music transcriptionMulti-pitch estimationDigital signal processingArtificial neural networksMachine learning and deep learningDomínio/Área Científica::Engenharia e Tecnologia::Engenharia Eletrotécnica, Eletrónica e InformáticaMusic transcription is the problem of detecting notes that are being played in a musical piece. This is a difficult task that only trained people are capable of doing. Due to its difficulty, there have been a high interest in automate it. However, automatic music transcription encompasses several fields of research such as, digital signal processing, machine learning, music theory and cognition, pitch perception and psychoacoustics. All of this, makes automatic music transcription an hard problem to solve. In this work we present a novel approach of automatically transcribing piano musical pieces using deep learning techniques. We take advantage of deep learning techniques to build several classifiers, each one responsible for detecting only one musical note. In theory, this division of work would enhance the ability of each classifier to transcribe. Apart from that, we also apply two additional stages, pre-processing and post-processing, to improve the efficiency of our system. The pre-processing stage aims at improving the quality of the input data before the classification/transcription stage, while the post-processing aims at fixing errors originated during the classification stage. In the initial steps, preliminary experiments have been performed to fine tune our model, in both three stages: pre-processing, classification and post-processing. The experimental setup, using those optimized techniques and parameters, is shown and a comparison is given with other two state-of-the-art works that apply the same dataset as well as the same deep learning technique but using a different approach. By different approach we mean that a single neural network is used to detect all the musical notes rather than one neural network per each note. Our approach was able to surpass in frame-based metrics these works, while reaching close results in onset-based metrics, demonstrating the feasability of our approach.Grilo, Carlos Fernando AlmeidaDomingues, Patrício RodriguesReis, Gustavo Miguel JorgeIC-OnlineGil, André Ferreira2019-08-20T13:43:00Z2019-05-212019-05-21T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisapplication/pdfhttp://hdl.handle.net/10400.8/4041TID:202276716enginfo:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2024-01-17T15:48:28Zoai:iconline.ipleiria.pt:10400.8/4041Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-20T01:48:00.553859Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse |
dc.title.none.fl_str_mv |
Automatic transcription of music using deep learning techniques |
title |
Automatic transcription of music using deep learning techniques |
spellingShingle |
Automatic transcription of music using deep learning techniques Gil, André Ferreira Automatic music transcription Multi-pitch estimation Digital signal processing Artificial neural networks Machine learning and deep learning Domínio/Área Científica::Engenharia e Tecnologia::Engenharia Eletrotécnica, Eletrónica e Informática |
title_short |
Automatic transcription of music using deep learning techniques |
title_full |
Automatic transcription of music using deep learning techniques |
title_fullStr |
Automatic transcription of music using deep learning techniques |
title_full_unstemmed |
Automatic transcription of music using deep learning techniques |
title_sort |
Automatic transcription of music using deep learning techniques |
author |
Gil, André Ferreira |
author_facet |
Gil, André Ferreira |
author_role |
author |
dc.contributor.none.fl_str_mv |
Grilo, Carlos Fernando Almeida Domingues, Patrício Rodrigues Reis, Gustavo Miguel Jorge IC-Online |
dc.contributor.author.fl_str_mv |
Gil, André Ferreira |
dc.subject.por.fl_str_mv |
Automatic music transcription Multi-pitch estimation Digital signal processing Artificial neural networks Machine learning and deep learning Domínio/Área Científica::Engenharia e Tecnologia::Engenharia Eletrotécnica, Eletrónica e Informática |
topic |
Automatic music transcription Multi-pitch estimation Digital signal processing Artificial neural networks Machine learning and deep learning Domínio/Área Científica::Engenharia e Tecnologia::Engenharia Eletrotécnica, Eletrónica e Informática |
description |
Music transcription is the problem of detecting notes that are being played in a musical piece. This is a difficult task that only trained people are capable of doing. Due to its difficulty, there have been a high interest in automate it. However, automatic music transcription encompasses several fields of research such as, digital signal processing, machine learning, music theory and cognition, pitch perception and psychoacoustics. All of this, makes automatic music transcription an hard problem to solve. In this work we present a novel approach of automatically transcribing piano musical pieces using deep learning techniques. We take advantage of deep learning techniques to build several classifiers, each one responsible for detecting only one musical note. In theory, this division of work would enhance the ability of each classifier to transcribe. Apart from that, we also apply two additional stages, pre-processing and post-processing, to improve the efficiency of our system. The pre-processing stage aims at improving the quality of the input data before the classification/transcription stage, while the post-processing aims at fixing errors originated during the classification stage. In the initial steps, preliminary experiments have been performed to fine tune our model, in both three stages: pre-processing, classification and post-processing. The experimental setup, using those optimized techniques and parameters, is shown and a comparison is given with other two state-of-the-art works that apply the same dataset as well as the same deep learning technique but using a different approach. By different approach we mean that a single neural network is used to detect all the musical notes rather than one neural network per each note. Our approach was able to surpass in frame-based metrics these works, while reaching close results in onset-based metrics, demonstrating the feasability of our approach. |
publishDate |
2019 |
dc.date.none.fl_str_mv |
2019-08-20T13:43:00Z 2019-05-21 2019-05-21T00:00:00Z |
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/10400.8/4041 TID:202276716 |
url |
http://hdl.handle.net/10400.8/4041 |
identifier_str_mv |
TID:202276716 |
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.format.none.fl_str_mv |
application/pdf |
dc.source.none.fl_str_mv |
reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação instacron:RCAAP |
instname_str |
Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
instacron_str |
RCAAP |
institution |
RCAAP |
reponame_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
collection |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository.name.fl_str_mv |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
repository.mail.fl_str_mv |
|
_version_ |
1799136973632307200 |