End-to-End Neural Optical Music Recognition of Monophonic Scores
Please use this identifier to cite or link to this item:
http://hdl.handle.net/10045/74947
Title: | End-to-End Neural Optical Music Recognition of Monophonic Scores |
---|---|
Authors: | Calvo-Zaragoza, Jorge | Rizo, David |
Research Group/s: | Reconocimiento de Formas e Inteligencia Artificial |
Center, Department or Service: | Universidad de Alicante. Departamento de Lenguajes y Sistemas Informáticos |
Keywords: | Optical Music Recognition | End-to-end recognition | Deep Learning | Music score images |
Knowledge Area: | Lenguajes y Sistemas Informáticos |
Issue Date: | 11-Apr-2018 |
Publisher: | MDPI |
Citation: | 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 |
Abstract: | 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. |
Sponsor: | 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 |
Language: | eng |
Type: | info:eu-repo/semantics/article |
Rights: | © 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/). |
Peer Review: | si |
Publisher version: | https://doi.org/10.3390/app8040606 |
Appears in Collections: | INV - GRFIA - Artículos de Revistas |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
2018_Calvo_Rizo_ApplSci.pdf | 3,68 MB | Adobe PDF | Open Preview | |
This item is licensed under a Creative Commons License