Applying deep learning techniques to estimate patterns of musical gesture

Repetitive practice is one of the most important factors in improving the performance of motor skills. This paper focuses on the analysis and classification of forearm gestures in the context of violin playing. We recorded five experts and three students performing eight traditional classical violin...

Descripción completa

Detalles Bibliográficos
Autores: Dalmazzo, David, Waddell, George, Ramírez, Rafael, 1966-
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2021
País:España
Institución:Universitat Pompeu Fabra
Repositorio:Repositorio Digital de la UPF
OAI Identifier:oai:repositori.upf.edu:10230/46473
Acceso en línea:http://hdl.handle.net/10230/46473
http://dx.doi.org/10.3389/fpsyg.2020.575971
Access Level:acceso abierto
Palabra clave:Gesture recognition
Bow-strokes
Music interaction
CNN
LSTM
Music education
ConvLSTM
CNN_LSTM
id ES_2d044245ea11ff2239956ebd5ce213a8
oai_identifier_str oai:repositori.upf.edu:10230/46473
network_acronym_str ES
network_name_str España
repository_id_str
spelling Applying deep learning techniques to estimate patterns of musical gestureDalmazzo, DavidWaddell, GeorgeRamírez, Rafael, 1966-Gesture recognitionBow-strokesMusic interactionCNNLSTMMusic educationConvLSTMCNN_LSTMRepetitive practice is one of the most important factors in improving the performance of motor skills. This paper focuses on the analysis and classification of forearm gestures in the context of violin playing. We recorded five experts and three students performing eight traditional classical violin bow-strokes: martelé, staccato, detaché, ricochet, legato, trémolo, collé, and col legno. To record inertial motion information, we utilized the Myo sensor, which reports a multidimensional time-series signal. We synchronized inertial motion recordings with audio data to extract the spatiotemporal dynamics of each gesture. Applying state-of-the-art deep neural networks, we implemented and compared different architectures where convolutional neural networks (CNN) models demonstrated recognition rates of 97.147%, 3DMultiHeaded_CNN models showed rates of 98.553%, and rates of 99.234% were demonstrated by CNN_LSTM models. The collected data (quaternion of the bowing arm of a violinist) contained sufficient information to distinguish the bowing techniques studied, and deep learning methods were capable of learning the movement patterns that distinguish these techniques. Each of the learning algorithms investigated (CNN, 3DMultiHeaded_CNN, and CNN_LSTM) produced high classification accuracies which supported the feasibility of training classifiers. The resulting classifiers may provide the foundation of a digital assistant to enhance musicians' time spent practicing alone, providing real-time feedback on the accuracy and consistency of their musical gestures in performance.This work has been partly sponsored by the Spanish TIN project TIMUL (TIN 2013-48152-C2-2-R), the European Union Horizon 2020 research and innovation program under grant agreement No. 688269 (TELMI project), and the Spanish Ministry of Economy and Competitiveness under the Maria de Maeztu Units of Excellence Programme (MDM-2015-0502).Frontiers202120212021info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfapplication/pdfhttp://hdl.handle.net/10230/46473http://dx.doi.org/10.3389/fpsyg.2020.575971reponame:Repositorio Digital de la UPFinstname:Universitat Pompeu FabraInglésFrontiers in Psychology. 2021 Jan 5;11:575971.info:eu-repo/grantAgreement/ES/1PE/TIN2013-48152-C2-2-Rinfo:eu-repo/grantAgreement/EC/H2020/688269© 2021 Dalmazzo, Waddell and Ramírez. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY) (https://creativecommons.org/licenses/by/4.0/). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.http://creativecommons.org/licenses/by/4.0/info:eu-repo/semantics/openAccessoai:repositori.upf.edu:10230/464732026-06-12T07:21:37Z
dc.title.none.fl_str_mv Applying deep learning techniques to estimate patterns of musical gesture
title Applying deep learning techniques to estimate patterns of musical gesture
spellingShingle Applying deep learning techniques to estimate patterns of musical gesture
Dalmazzo, David
Gesture recognition
Bow-strokes
Music interaction
CNN
LSTM
Music education
ConvLSTM
CNN_LSTM
title_short Applying deep learning techniques to estimate patterns of musical gesture
title_full Applying deep learning techniques to estimate patterns of musical gesture
title_fullStr Applying deep learning techniques to estimate patterns of musical gesture
title_full_unstemmed Applying deep learning techniques to estimate patterns of musical gesture
title_sort Applying deep learning techniques to estimate patterns of musical gesture
dc.creator.none.fl_str_mv Dalmazzo, David
Waddell, George
Ramírez, Rafael, 1966-
author Dalmazzo, David
author_facet Dalmazzo, David
Waddell, George
Ramírez, Rafael, 1966-
author_role author
author2 Waddell, George
Ramírez, Rafael, 1966-
author2_role author
author
dc.subject.none.fl_str_mv Gesture recognition
Bow-strokes
Music interaction
CNN
LSTM
Music education
ConvLSTM
CNN_LSTM
topic Gesture recognition
Bow-strokes
Music interaction
CNN
LSTM
Music education
ConvLSTM
CNN_LSTM
description Repetitive practice is one of the most important factors in improving the performance of motor skills. This paper focuses on the analysis and classification of forearm gestures in the context of violin playing. We recorded five experts and three students performing eight traditional classical violin bow-strokes: martelé, staccato, detaché, ricochet, legato, trémolo, collé, and col legno. To record inertial motion information, we utilized the Myo sensor, which reports a multidimensional time-series signal. We synchronized inertial motion recordings with audio data to extract the spatiotemporal dynamics of each gesture. Applying state-of-the-art deep neural networks, we implemented and compared different architectures where convolutional neural networks (CNN) models demonstrated recognition rates of 97.147%, 3DMultiHeaded_CNN models showed rates of 98.553%, and rates of 99.234% were demonstrated by CNN_LSTM models. The collected data (quaternion of the bowing arm of a violinist) contained sufficient information to distinguish the bowing techniques studied, and deep learning methods were capable of learning the movement patterns that distinguish these techniques. Each of the learning algorithms investigated (CNN, 3DMultiHeaded_CNN, and CNN_LSTM) produced high classification accuracies which supported the feasibility of training classifiers. The resulting classifiers may provide the foundation of a digital assistant to enhance musicians' time spent practicing alone, providing real-time feedback on the accuracy and consistency of their musical gestures in performance.
publishDate 2021
dc.date.none.fl_str_mv 2021
2021
2021
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/10230/46473
http://dx.doi.org/10.3389/fpsyg.2020.575971
url http://hdl.handle.net/10230/46473
http://dx.doi.org/10.3389/fpsyg.2020.575971
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv Frontiers in Psychology. 2021 Jan 5;11:575971.
info:eu-repo/grantAgreement/ES/1PE/TIN2013-48152-C2-2-R
info:eu-repo/grantAgreement/EC/H2020/688269
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 Frontiers
publisher.none.fl_str_mv Frontiers
dc.source.none.fl_str_mv reponame:Repositorio Digital de la UPF
instname:Universitat Pompeu Fabra
instname_str Universitat Pompeu Fabra
reponame_str Repositorio Digital de la UPF
collection Repositorio Digital de la UPF
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869405281819033600
score 15,812429