End-to-End Neural Optical Music Recognition of Monophonic Scores

Por favor, use este identificador para citar o enlazar este ítem: http://hdl.handle.net/10045/74947
Información del item - Informació de l'item - Item information
Título: End-to-End Neural Optical Music Recognition of Monophonic Scores
Autor/es: Calvo-Zaragoza, Jorge | Rizo, David
Grupo/s de investigación o GITE: Reconocimiento de Formas e Inteligencia Artificial
Centro, Departamento o Servicio: Universidad de Alicante. Departamento de Lenguajes y Sistemas Informáticos
Palabras clave: Optical Music Recognition | End-to-end recognition | Deep Learning | Music score images
Área/s de conocimiento: Lenguajes y Sistemas Informáticos
Fecha de publicación: 11-abr-2018
Editor: MDPI
Cita bibliográfica: Calvo-Zaragoza J, Rizo D. End-to-End Neural Optical Music Recognition of Monophonic Scores. Applied Sciences. 2018; 8(4):606. doi:10.3390/app8040606
Resumen: Optical Music Recognition is a field of research that investigates how to computationally decode music notation from images. Despite the efforts made so far, there are hardly any complete solutions to the problem. In this work, we study the use of neural networks that work in an end-to-end manner. This is achieved by using a neural model that combines the capabilities of convolutional neural networks, which work on the input image, and recurrent neural networks, which deal with the sequential nature of the problem. Thanks to the use of the the so-called Connectionist Temporal Classification loss function, these models can be directly trained from input images accompanied by their corresponding transcripts into music symbol sequences. We also present the Printed Music Scores dataset, containing more than 80,000 monodic single-staff real scores in common western notation, that is used to train and evaluate the neural approach. In our experiments, it is demonstrated that this formulation can be carried out successfully. Additionally, we study several considerations about the codification of the output musical sequences, the convergence and scalability of the neural models, as well as the ability of this approach to locate symbols in the input score.Optical Music Recognition is a field of research that investigates how to computationally decode music notation from images. Despite the efforts made so far, there are hardly any complete solutions to the problem. In this work, we study the use of neural networks that work in an end-to-end manner. This is achieved by using a neural model that combines the capabilities of convolutional neural networks, which work on the input image, and recurrent neural networks, which deal with the sequential nature of the problem. Thanks to the use of the the so-called Connectionist Temporal Classification loss function, these models can be directly trained from input images accompanied by their corresponding transcripts into music symbol sequences. We also present the Printed Music Scores dataset, containing more than 80,000 monodic single-staff real scores in common western notation, that is used to train and evaluate the neural approach. In our experiments, it is demonstrated that this formulation can be carried out successfully. Additionally, we study several considerations about the codification of the output musical sequences, the convergence and scalability of the neural models, as well as the ability of this approach to locate symbols in the input score.
Patrocinador/es: This work was supported by the Social Sciences and Humanities Research Council of Canada, and the Spanish Ministerio de Economía y Competitividad through Project HISPAMUS Ref. No. TIN2017-86576-R (supported by UE FEDER funds).
URI: http://hdl.handle.net/10045/74947
ISSN: 2076-3417
DOI: 10.3390/app8040606
Idioma: eng
Tipo: info:eu-repo/semantics/article
Derechos: © 2018 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
Revisión científica: si
Versión del editor: https://doi.org/10.3390/app8040606
Aparece en las colecciones:INV - GRFIA - Artículos de Revistas

Archivos en este ítem:
Archivos en este ítem:
Archivo Descripción TamañoFormato 
Thumbnail2018_Calvo_Rizo_ApplSci.pdf3,68 MBAdobe PDFAbrir Vista previa


Este ítem está licenciado bajo Licencia Creative Commons Creative Commons