2021
Castellanos, F. J.; Gallego, A. J.; Calvo-Zaragoza, J.
Unsupervised Neural Domain Adaptation for Document Image Binarization Journal Article
In: Pattern Recognition, vol. 119, pp. 108099, 2021.
BibTeX | Tags: GRE19-04, HispaMus
@article{k467,
title = {Unsupervised Neural Domain Adaptation for Document Image Binarization},
author = {F. J. Castellanos and A. J. Gallego and J. Calvo-Zaragoza},
year = {2021},
date = {2021-11-01},
urldate = {2021-11-01},
journal = {Pattern Recognition},
volume = {119},
pages = {108099},
keywords = {GRE19-04, HispaMus},
pubstate = {published},
tppubtype = {article}
}
Gallego, A. J.; Calvo-Zaragoza, J.; Fisher, R. B.
Incremental Unsupervised Domain-Adversarial Training of Neural Networks Journal Article
In: IEEE Transactions on Neural Networks and Learning Systems, vol. 32, no. 11, pp. 4864-4878, 2021, ISSN: 2162-2388.
Abstract | Links | BibTeX | Tags: GRE19-04, HispaMus
@article{k455,
title = {Incremental Unsupervised Domain-Adversarial Training of Neural Networks},
author = {A. J. Gallego and J. Calvo-Zaragoza and R. B. Fisher},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/455/2001.04129.pdf},
issn = {2162-2388},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
journal = {IEEE Transactions on Neural Networks and Learning Systems},
volume = {32},
number = {11},
pages = {4864-4878},
abstract = {In the context of supervised statistical learning, it is typically assumed that the training set comes from the same distribution that draws the test samples. When this is not the case, the behavior of the learned model is unpredictable and becomes dependent upon the degree of similarity between the distribution of the training set and the distribution of the test set. One of the research topics that investigates this scenario is referred to as Domain Adaptation (DA). Deep neural networks brought dramatic advances in pattern recognition and that is why there have been many attempts to provide good domain adaptation algorithms for these models. Here we take a different avenue and approach the problem from an incremental point of view, where the model is adapted to the new domain iteratively. We make use of an existing unsupervised domain-adaptation algorithm to identify the target samples on which there is greater confidence about their true label. The output of the model is analyzed in different ways to determine the candidate samples. The selected samples are then added to the source training set by self-labeling, and the process is repeated until all target samples are labeled. This approach implements a form of adversarial training in which, by moving the self-labeled samples from the target to the source set, the DA algorithm is forced to look for new features after each iteration. Our results report a clear improvement with respect to the non-incremental case in several datasets, also outperforming other state-of-the-art domain adaptation algorithms.},
keywords = {GRE19-04, HispaMus},
pubstate = {published},
tppubtype = {article}
}
In the context of supervised statistical learning, it is typically assumed that the training set comes from the same distribution that draws the test samples. When this is not the case, the behavior of the learned model is unpredictable and becomes dependent upon the degree of similarity between the distribution of the training set and the distribution of the test set. One of the research topics that investigates this scenario is referred to as Domain Adaptation (DA). Deep neural networks brought dramatic advances in pattern recognition and that is why there have been many attempts to provide good domain adaptation algorithms for these models. Here we take a different avenue and approach the problem from an incremental point of view, where the model is adapted to the new domain iteratively. We make use of an existing unsupervised domain-adaptation algorithm to identify the target samples on which there is greater confidence about their true label. The output of the model is analyzed in different ways to determine the candidate samples. The selected samples are then added to the source training set by self-labeling, and the process is repeated until all target samples are labeled. This approach implements a form of adversarial training in which, by moving the self-labeled samples from the target to the source set, the DA algorithm is forced to look for new features after each iteration. Our results report a clear improvement with respect to the non-incremental case in several datasets, also outperforming other state-of-the-art domain adaptation algorithms. Román, M. A.
An End-to-End Framework for Audio-to-Score Music Transcription PhD Thesis
2021.
@phdthesis{k462,
title = {An End-to-End Framework for Audio-to-Score Music Transcription},
author = {M. A. Román},
editor = {J. Calvo-Zaragoza and A. Pertusa},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
organization = {Universidad de Alicante},
keywords = {HispaMus},
pubstate = {published},
tppubtype = {phdthesis}
}
Calvo-Zaragoza, J.; Rizo, D.; Iñesta, J. M.
Reconocimiento Óptico de Partituras (OMR) aplicado al Fonde de Música Tradicional IMF-CSIC Book Chapter
In: Gambero-Ustárroz, M.; Ros-Fábregas, E. (Ed.): Musicología en Web. Patrimonio musical y Humanidades Digitales, Chapter 4, pp. 87-109, Edition Reichenberger, 2021, ISBN: 978-3-967280-14-2.
@inbook{k470,
title = {Reconocimiento Óptico de Partituras (OMR) aplicado al Fonde de Música Tradicional IMF-CSIC},
author = {J. Calvo-Zaragoza and D. Rizo and J. M. Iñesta},
editor = {M. Gambero-Ustárroz and E. Ros-Fábregas},
isbn = {978-3-967280-14-2},
year = {2021},
date = {2021-01-01},
booktitle = {Musicología en Web. Patrimonio musical y Humanidades Digitales},
pages = {87-109},
publisher = {Edition Reichenberger},
chapter = {4},
keywords = {HispaMus},
pubstate = {published},
tppubtype = {inbook}
}
Castellanos, F. J.; Valero-Mas, J. J.; Calvo-Zaragoza, J.
Prototype Generation in the String Space via Approximate Median for Data Reduction in Nearest Neighbor classification Journal Article
In: Soft Computing, vol. 25, 2021, ISSN: 15403-15415.
BibTeX | Tags: GRE19-04, HispaMus
@article{k476,
title = {Prototype Generation in the String Space via Approximate Median for Data Reduction in Nearest Neighbor classification},
author = {F. J. Castellanos and J. J. Valero-Mas and J. Calvo-Zaragoza},
issn = {15403-15415},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
journal = {Soft Computing},
volume = {25},
keywords = {GRE19-04, HispaMus},
pubstate = {published},
tppubtype = {article}
}
2020
Ríos-Vila, A.; Calvo-Zaragoza, J.; Rizo, D.
Evaluating Simultaneous Recognition and Encoding for Optical Music Recognition Proceedings Article
In: DLfM 2020: 7th International Conference on Digital Libraries for Musicology, pp. 10-17, Association for Computing Machinery, 2020, ISBN: 978-1-4503-8760-6.
@inproceedings{k456,
title = {Evaluating Simultaneous Recognition and Encoding for Optical Music Recognition},
author = {A. Ríos-Vila and J. Calvo-Zaragoza and D. Rizo},
isbn = {978-1-4503-8760-6},
year = {2020},
date = {2020-10-01},
booktitle = {DLfM 2020: 7th International Conference on Digital Libraries for Musicology},
journal = {DLfM 2020: 7th International Conference on Digital Libraries for Musicology},
pages = {10-17},
publisher = {Association for Computing Machinery},
keywords = {HispaMus},
pubstate = {published},
tppubtype = {inproceedings}
}
Castellanos, F. J.; Calvo-Zaragoza, J.; Iñesta, J. M.
A neural approach for full-page Optical Music Recognition of mensural documents Proceedings Article
In: Proceedings of the 21st International Society for Music Information Retrieval Conference, pp. 558-565, Montréal, Canada, 2020, ISBN: 978-0-9813537-0-8.
@inproceedings{k457,
title = {A neural approach for full-page Optical Music Recognition of mensural documents},
author = {F. J. Castellanos and J. Calvo-Zaragoza and J. M. Iñesta},
isbn = {978-0-9813537-0-8},
year = {2020},
date = {2020-10-01},
booktitle = {Proceedings of the 21st International Society for Music Information Retrieval Conference},
pages = {558-565},
address = {Montréal, Canada},
keywords = {HispaMus},
pubstate = {published},
tppubtype = {inproceedings}
}
Castellanos, F. J.; Calvo-Zaragoza, J.; Iñesta, J. M.
Two-step neural cross-domain experiments forfull-page recognition of Mensural documents Proceedings Article
In: Proc. of the 13th International Workshop on Machine Learning and Music, pp. 56–60, MML 2020 13th International Workshop on Machine Learning and Music, 2020.
BibTeX | Tags: GRE19-04, HispaMus
@inproceedings{k448,
title = {Two-step neural cross-domain experiments forfull-page recognition of Mensural documents},
author = {F. J. Castellanos and J. Calvo-Zaragoza and J. M. Iñesta},
year = {2020},
date = {2020-09-01},
booktitle = {Proc. of the 13th International Workshop on Machine Learning and Music},
pages = {56--60},
publisher = {13th International Workshop on Machine Learning and Music},
organization = {MML 2020},
keywords = {GRE19-04, HispaMus},
pubstate = {published},
tppubtype = {inproceedings}
}
Thomae, M. E.; Ríos-Vila, A.; Calvo-Zaragoza, J.; Rizo, D.; Iñesta, J. M.
Retrieving Music Semantics from Optical Music Recognition by Machine Translation Proceedings Article
In: Luca, Elsa De; Flanders, Julia (Ed.): Music Encoding Conference Proceedings 26-29 May, 2020 Tufts University, Boston (USA), pp. 19-24, Music Encoding Initiative 2020.
Links | BibTeX | Tags: HispaMus
@inproceedings{k446,
title = {Retrieving Music Semantics from Optical Music Recognition by Machine Translation},
author = {M. E. Thomae and A. Ríos-Vila and J. Calvo-Zaragoza and D. Rizo and J. M. Iñesta},
editor = {Elsa De Luca and Julia Flanders},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/446/music_encoding_conference_proceedings_2020.pdf},
year = {2020},
date = {2020-05-01},
booktitle = {Music Encoding Conference Proceedings 26-29 May, 2020 Tufts University, Boston (USA)},
pages = {19-24},
organization = {Music Encoding Initiative},
keywords = {HispaMus},
pubstate = {published},
tppubtype = {inproceedings}
}
Calvo-Zaragoza, J.; Jr., J. Hajic; Pacha, A.
Understanding Optical Music Recognition Journal Article
In: ACM Computing Surveys, vol. 53, no. 4, pp. 77, 2020.
@article{k426,
title = {Understanding Optical Music Recognition},
author = {J. Calvo-Zaragoza and J. Hajic Jr. and A. Pacha},
year = {2020},
date = {2020-01-01},
journal = {ACM Computing Surveys},
volume = {53},
number = {4},
pages = {77},
keywords = {HispaMus},
pubstate = {published},
tppubtype = {article}
}
Gallego, A. J.; Calvo-Zaragoza, J.; Rico-Juan, J. R.
Insights Into Efficient k-Nearest Neighbor Classification With Convolutional Neural Codes Journal Article
In: IEEE Access, vol. 8, pp. 99312-99326, 2020, ISSN: 2169-3536.
Abstract | BibTeX | Tags: HispaMus
@article{k444,
title = {Insights Into Efficient k-Nearest Neighbor Classification With Convolutional Neural Codes},
author = {A. J. Gallego and J. Calvo-Zaragoza and J. R. Rico-Juan},
issn = {2169-3536},
year = {2020},
date = {2020-01-01},
urldate = {2020-01-01},
journal = {IEEE Access},
volume = {8},
pages = {99312-99326},
abstract = {The increasing consideration of Convolutional Neural Networks (CNN) has not prevented the use of the k-Nearest Neighbor (kNN) method. In fact, a hybrid CNN-kNN approach is an interesting option in which the network specializes in feature extraction through its activations (Neural Codes), while the kNN has the advantage of performing a retrieval by means of similarity. However, this hybrid approach also has the disadvantages of the kNN search, and especially its high computational cost which is, in principle, undesirable for large-scale data. In this paper, we present the first comprehensive study of efficient kNN search algorithms using this hybrid CNN-kNN approach. This has been done by considering up to 16 different algorithms, each of which is evaluated with a different parametrization, in 7 datasets of heterogeneous composition. Our results show that no single algorithm is capable of covering all aspects, but rather that each family of algorithms is better suited to specific aspects of the problem. This signifies that Fast Similarity Search algorithms maintain their performance, but do not reduce the cost as much as the Data Reduction family does. In turn, the Approximated Similarity Search family is postulated as a good option when attempting to balance accuracy and efficiency. The experiments also suggest that considering statistical transformation algorithms such as Linear Discriminant Analysis might be useful in certain cases.},
keywords = {HispaMus},
pubstate = {published},
tppubtype = {article}
}
The increasing consideration of Convolutional Neural Networks (CNN) has not prevented the use of the k-Nearest Neighbor (kNN) method. In fact, a hybrid CNN-kNN approach is an interesting option in which the network specializes in feature extraction through its activations (Neural Codes), while the kNN has the advantage of performing a retrieval by means of similarity. However, this hybrid approach also has the disadvantages of the kNN search, and especially its high computational cost which is, in principle, undesirable for large-scale data. In this paper, we present the first comprehensive study of efficient kNN search algorithms using this hybrid CNN-kNN approach. This has been done by considering up to 16 different algorithms, each of which is evaluated with a different parametrization, in 7 datasets of heterogeneous composition. Our results show that no single algorithm is capable of covering all aspects, but rather that each family of algorithms is better suited to specific aspects of the problem. This signifies that Fast Similarity Search algorithms maintain their performance, but do not reduce the cost as much as the Data Reduction family does. In turn, the Approximated Similarity Search family is postulated as a good option when attempting to balance accuracy and efficiency. The experiments also suggest that considering statistical transformation algorithms such as Linear Discriminant Analysis might be useful in certain cases. Ríos-Vila, A.; Calvo-Zaragoza, J.; Iñesta, J. M.
Exploring the two-dimensional nature of music notation for score recognition with end-to-end approaches Proceedings Article
In: Proc. of 17th International Conference on Frontiers in Handwriting Recognition (ICFHR), pp. 193–198, IEEE Computer Society IEEE, Dormund (Germany), 2020, ISBN: 978-1-7281-9966-5.
Abstract | BibTeX | Tags: HispaMus
@inproceedings{k461,
title = {Exploring the two-dimensional nature of music notation for score recognition with end-to-end approaches},
author = {A. Ríos-Vila and J. Calvo-Zaragoza and J. M. Iñesta},
isbn = {978-1-7281-9966-5},
year = {2020},
date = {2020-01-01},
booktitle = {Proc. of 17th International Conference on Frontiers in Handwriting Recognition (ICFHR)},
pages = {193--198},
publisher = {IEEE},
address = {Dormund (Germany)},
organization = {IEEE Computer Society},
abstract = {Optical Music Recognition workflows perform several steps to retrieve the content in music score images, being symbol recognition one of the key stages. State-of-the-art approaches for this stage currently address the coding of the output symbols as if they were plain text characters. However, music symbols have a two-dimensional nature that is ignored in these approaches. In this paper, we explore alternative output representations to perform music symbol recognition with state-of-the-art end-to-end neural technologies. We propose and describe new output representations which take into account the mentioned two-dimensional nature. We seek answers to the question of whether it is possible to obtain better recognition results in both printed and handwritten music scores. In this analysis, we compare the results given using three output encodings and two neural approaches. We found that one of the proposed encodings outperforms the results obtained by the standard one. This permits us to conclude that it is interesting to keep researching on this topic to improve end-to-end music score recognition.},
keywords = {HispaMus},
pubstate = {published},
tppubtype = {inproceedings}
}
Optical Music Recognition workflows perform several steps to retrieve the content in music score images, being symbol recognition one of the key stages. State-of-the-art approaches for this stage currently address the coding of the output symbols as if they were plain text characters. However, music symbols have a two-dimensional nature that is ignored in these approaches. In this paper, we explore alternative output representations to perform music symbol recognition with state-of-the-art end-to-end neural technologies. We propose and describe new output representations which take into account the mentioned two-dimensional nature. We seek answers to the question of whether it is possible to obtain better recognition results in both printed and handwritten music scores. In this analysis, we compare the results given using three output encodings and two neural approaches. We found that one of the proposed encodings outperforms the results obtained by the standard one. This permits us to conclude that it is interesting to keep researching on this topic to improve end-to-end music score recognition. Rizo, D.; Calvo-Zaragoza, J.; Iñesta, J. M.
Preservación del patrimonio musical mediante transcripción asistida por ordenador Book Chapter
In: Isusi-Fagoaga, R.; Serrano, F. Villanueva (Ed.): La música de la Corona d’Aragó: investigació, transferència i educació, Chapter 15, pp. 275–298, Universitat de València, 2020, ISBN: 978-84-09-19985-3.
@inbook{k466,
title = {Preservación del patrimonio musical mediante transcripción asistida por ordenador},
author = {D. Rizo and J. Calvo-Zaragoza and J. M. Iñesta},
editor = {R. Isusi-Fagoaga and F. Villanueva Serrano},
isbn = {978-84-09-19985-3},
year = {2020},
date = {2020-01-01},
urldate = {2020-01-01},
booktitle = {La música de la Corona d’Aragó: investigació, transferència i educació},
pages = {275--298},
publisher = {Universitat de València},
chapter = {15},
keywords = {HispaMus},
pubstate = {published},
tppubtype = {inbook}
}
2019
Calvo-Zaragoza, J.; Toselli, A. H.; Vidal, E.
Handwritten Music Recognition for Mensural Notation with Convolutional Recurrent Neural Networks Journal Article
In: Pattern Recognition Letters, vol. 128, pp. 115–121, 2019.
Links | BibTeX | Tags: HispaMus
@article{k415,
title = {Handwritten Music Recognition for Mensural Notation with Convolutional Recurrent Neural Networks},
author = {J. Calvo-Zaragoza and A. H. Toselli and E. Vidal},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/415/1-s2.0-S0167865519302338-main.pdf},
year = {2019},
date = {2019-12-01},
journal = {Pattern Recognition Letters},
volume = {128},
pages = {115--121},
keywords = {HispaMus},
pubstate = {published},
tppubtype = {article}
}
Iñesta, J. M.; Rizo, D.; Calvo-Zaragoza, J.
MuRET as a software for the transcription of historical archives Proceedings Article
In: Proceedings of the 2nd Workshop on Reading Music Systems, WoRMS, pp. 12–15, Delft (The Nederlands), 2019.
Abstract | Links | BibTeX | Tags: HispaMus
@inproceedings{k437,
title = {MuRET as a software for the transcription of historical archives},
author = {J. M. Iñesta and D. Rizo and J. Calvo-Zaragoza},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/437/worms-2019-inesta.pdf},
year = {2019},
date = {2019-11-01},
booktitle = {Proceedings of the 2nd Workshop on Reading Music Systems, WoRMS},
pages = {12--15},
address = {Delft (The Nederlands)},
abstract = {The transcription process from historical hand- written music manuscripts to a structured digital encoding has been traditionally performed following a fully manual workflow. At most, it has received some technological support in particular stages, like optical music recognition (OMR) of the source images, or transcription to modern notation with music edition applications. Currently, there is no mature and stable enough solution for the OMR problem, and the most used music editors do not support early notations, such as the mensural notation. A new tool called MUsic Recognition, Encoding, and Transcription (MuRET) has been developed, which covers all transcription phases, from the manuscript image to the encoded digital content. MuRET is designed as a machine-learning based research tool, allowing different processing approaches to be used, and producing both the expected transcribed contents in standard encodings and data for the study of the transcription process.},
keywords = {HispaMus},
pubstate = {published},
tppubtype = {inproceedings}
}
The transcription process from historical hand- written music manuscripts to a structured digital encoding has been traditionally performed following a fully manual workflow. At most, it has received some technological support in particular stages, like optical music recognition (OMR) of the source images, or transcription to modern notation with music edition applications. Currently, there is no mature and stable enough solution for the OMR problem, and the most used music editors do not support early notations, such as the mensural notation. A new tool called MUsic Recognition, Encoding, and Transcription (MuRET) has been developed, which covers all transcription phases, from the manuscript image to the encoded digital content. MuRET is designed as a machine-learning based research tool, allowing different processing approaches to be used, and producing both the expected transcribed contents in standard encodings and data for the study of the transcription process. Ríos-Vila, A.; Calvo-Zaragoza, J.; Rizo, D.; Iñesta, J. M.
ReadSco: An Open-Source Web-Based Optical Music Recognition Tool Proceedings Article
In: Calvo-Zaragoza, J.; Pacha, A. (Ed.): Proc. of the 2nd International Workshop on Reading Music Systems, WoRMS 2019, pp. 27-30, Delft (The Netherlands), 2019.
Abstract | Links | BibTeX | Tags: HispaMus
@inproceedings{k439,
title = {ReadSco: An Open-Source Web-Based Optical Music Recognition Tool},
author = {A. Ríos-Vila and J. Calvo-Zaragoza and D. Rizo and J. M. Iñesta},
editor = {J. Calvo-Zaragoza and A. Pacha},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/439/ReadSco_Worms2019.pdf},
year = {2019},
date = {2019-11-01},
urldate = {2019-11-01},
booktitle = {Proc. of the 2nd International Workshop on Reading Music Systems, WoRMS 2019},
pages = {27-30},
address = {Delft (The Netherlands)},
abstract = {We introduce READSCO, an open-source web-based community tool for Optical Music Recognition. READSCO aims to serve as a connection between research results and practical use. We describe the design decisions considered to both favours a rapid integration of new advances from the research field and
facilitate the community’s participation in its development. The project is still in its planning phase, so this work is a good opportunity to present the main idea and get direct feedback from other researchers.},
keywords = {HispaMus},
pubstate = {published},
tppubtype = {inproceedings}
}
We introduce READSCO, an open-source web-based community tool for Optical Music Recognition. READSCO aims to serve as a connection between research results and practical use. We describe the design decisions considered to both favours a rapid integration of new advances from the research field and
facilitate the community’s participation in its development. The project is still in its planning phase, so this work is a good opportunity to present the main idea and get direct feedback from other researchers. Iñesta, J. M.; Rizo, D.; Calvo-Zaragoza, J.
Recognition, encoding, and transcription of early mensural handwritten music Proceedings Article
In: procedings of the 13th International Workshop on Graphics Recognition (GREC 2019), pp. 13-14, Sydney (Australia), 2019.
@inproceedings{k416,
title = {Recognition, encoding, and transcription of early mensural handwritten music},
author = {J. M. Iñesta and D. Rizo and J. Calvo-Zaragoza},
year = {2019},
date = {2019-09-01},
booktitle = {procedings of the 13th International Workshop on Graphics Recognition (GREC 2019)},
pages = {13-14},
address = {Sydney (Australia)},
keywords = {HispaMus},
pubstate = {published},
tppubtype = {inproceedings}
}
Alfaro-Contreras, M.; Calvo-Zaragoza, J.; Iñesta, J. M.
Approaching End-to-end Optical Music Recognition for Homophonic Scores Proceedings Article
In: Iberian Conference on Pattern Recognition and Image Analysis, IbPRIA 2019, pp. 147–158, Springer, Madrid, 2019, ISBN: 978-3-030-31321-0.
Links | BibTeX | Tags: HispaMus
@inproceedings{k419,
title = {Approaching End-to-end Optical Music Recognition for Homophonic Scores},
author = {M. Alfaro-Contreras and J. Calvo-Zaragoza and J. M. Iñesta},
url = {https://link.springer.com/chapter/10.1007/978-3-030-31321-0_13},
isbn = {978-3-030-31321-0},
year = {2019},
date = {2019-08-01},
urldate = {2019-08-01},
booktitle = {Iberian Conference on Pattern Recognition and Image Analysis, IbPRIA 2019},
pages = {147--158},
publisher = {Springer},
address = {Madrid},
keywords = {HispaMus},
pubstate = {published},
tppubtype = {inproceedings}
}
Mateiu, T. N.; Gallego, A. J.; Calvo-Zaragoza, J.
Domain Adaptation for Handwritten Symbol Recognition: A Case of Study in Old Music Manuscripts Proceedings Article
In: Iberian Conference on Pattern Recognition and Image Analysis, IbPRIA, pp. 135–146, Springer International Publishing, Madrid, Spain, 2019, ISBN: 978-3-030-31321-0.
Abstract | BibTeX | Tags: HispaMus
@inproceedings{k410,
title = {Domain Adaptation for Handwritten Symbol Recognition: A Case of Study in Old Music Manuscripts},
author = {T. N. Mateiu and A. J. Gallego and J. Calvo-Zaragoza},
isbn = {978-3-030-31321-0},
year = {2019},
date = {2019-07-01},
urldate = {2019-07-01},
booktitle = {Iberian Conference on Pattern Recognition and Image Analysis, IbPRIA},
pages = {135--146},
publisher = {Springer International Publishing},
address = {Madrid, Spain},
abstract = {The existence of a large amount of untranscripted music manuscripts has caused initiatives that use Machine Learning (ML) for Optical Music Recognition, in order to efficiently transcribe the music sources into a machine-readable format. Although most music manuscript are similar in nature, they inevitably vary from one another. This fact can negatively influence the complexity of the classification task because most ML models fail to transfer their knowledge from one domain to another, thereby requiring learning from scratch on new domains after manually labeling new data. This work studies the ability of a Domain Adversarial Neural Network for domain adaptation in the context of classifying handwritten music symbols. The main idea is to exploit the knowledge of a specific manuscript to classify symbols from different (unlabeled) manuscripts. The reported results are promising, obtaining a substantial improvement over a conventional Convolutional Neural Network approach, which can be used as a basis for future research.},
keywords = {HispaMus},
pubstate = {published},
tppubtype = {inproceedings}
}
The existence of a large amount of untranscripted music manuscripts has caused initiatives that use Machine Learning (ML) for Optical Music Recognition, in order to efficiently transcribe the music sources into a machine-readable format. Although most music manuscript are similar in nature, they inevitably vary from one another. This fact can negatively influence the complexity of the classification task because most ML models fail to transfer their knowledge from one domain to another, thereby requiring learning from scratch on new domains after manually labeling new data. This work studies the ability of a Domain Adversarial Neural Network for domain adaptation in the context of classifying handwritten music symbols. The main idea is to exploit the knowledge of a specific manuscript to classify symbols from different (unlabeled) manuscripts. The reported results are promising, obtaining a substantial improvement over a conventional Convolutional Neural Network approach, which can be used as a basis for future research. Nuñez-Alcover, Alicia; León, P. J. Ponce; Calvo-Zaragoza, J.
Glyph and Position Classification of Music Symbols in Early Music Manuscripts Proceedings Article
In: Morales, A.; Fierrez, J.; Sánchez, J. Salvador; Ribeiro, B. (Ed.): Proc. of the 9th Iberian Conference on Pattern Recognition and Image Analysis, LNCS vol. 11867, pp. 159-168, AERFAI, APRP Springer, Madrid, Spain, 2019, ISBN: 978-3-030-31331-9.
Abstract | Links | BibTeX | Tags: HispaMus
@inproceedings{k420,
title = {Glyph and Position Classification of Music Symbols in Early Music Manuscripts},
author = {Alicia Nuñez-Alcover and P. J. Ponce León and J. Calvo-Zaragoza},
editor = {A. Morales and J. Fierrez and J. Salvador Sánchez and B. Ribeiro},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/420/IbPRIA2019_paper_91-1.pdf},
isbn = {978-3-030-31331-9},
year = {2019},
date = {2019-07-01},
booktitle = {Proc. of the 9th Iberian Conference on Pattern Recognition and Image Analysis, LNCS vol. 11867},
pages = {159-168},
publisher = {Springer},
address = {Madrid, Spain},
organization = {AERFAI, APRP},
abstract = {Optical Music Recognition is a field of research that automates the reading of musical scores so as to transcribe their content into a structured digital format. When dealing with music manuscripts, the traditional workflow establishes separate stages of detection and classification of musical symbols. In the latter, most of the research has focused on detecting musical glyphs, ignoring that the meaning of a musical symbol is defined by two components: its glyph and its position within the staff. In this paper we study how to perform both glyph and position classification of handwritten musical symbols in early music manuscripts written in white Mensural notation, a common notation system used for the most part of the XVI and XVII centuries. We make use of Convolutional Neural Networks as the classification method, and we tested several alternatives such as using independent models for each component, combining label spaces, or using both multi-input and multi-output models. Our results on early music manuscripts provide insights about the effectiveness and efficiency of each approach.},
keywords = {HispaMus},
pubstate = {published},
tppubtype = {inproceedings}
}
Optical Music Recognition is a field of research that automates the reading of musical scores so as to transcribe their content into a structured digital format. When dealing with music manuscripts, the traditional workflow establishes separate stages of detection and classification of musical symbols. In the latter, most of the research has focused on detecting musical glyphs, ignoring that the meaning of a musical symbol is defined by two components: its glyph and its position within the staff. In this paper we study how to perform both glyph and position classification of handwritten musical symbols in early music manuscripts written in white Mensural notation, a common notation system used for the most part of the XVI and XVII centuries. We make use of Convolutional Neural Networks as the classification method, and we tested several alternatives such as using independent models for each component, combining label spaces, or using both multi-input and multi-output models. Our results on early music manuscripts provide insights about the effectiveness and efficiency of each approach. Garay-Maestre, U.; Gallego, A. J.; Calvo-Zaragoza, J.
Data Augmentation via Variational Auto-Encoders Proceedings Article
In: Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications, pp. 29–37, 2019, ISBN: 978-3-030-13469-3.
Abstract | BibTeX | Tags: HispaMus
@inproceedings{k406,
title = {Data Augmentation via Variational Auto-Encoders},
author = {U. Garay-Maestre and A. J. Gallego and J. Calvo-Zaragoza},
isbn = {978-3-030-13469-3},
year = {2019},
date = {2019-01-01},
urldate = {2019-01-01},
booktitle = {Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications},
pages = {29--37},
abstract = {Data augmentation is a widely considered technique to improve the performance of Convolutional Neural Networks during training. This step consists in synthetically generate new labeled data by perturbing the samples of the training set, which is expected to provide more robustness to the learning process. The problem is that the augmentation procedure has to be adjusted manually because the perturbations considered must make sense for the task at issue. In this paper we propose the use of Variational Auto-Encoders (VAEs) to generate new synthetic samples, instead of resorting to heuristic strategies. VAEs are powerful generative models that learn a parametric latent space of the input domain from which new samples can be generated. In our experiments over the well-known MNIST dataset, the data augmentation by VAEs improves the base results, yet to a lesser extent of that obtained by a well-adjusted conventional data augmentation. However, the combination of both conventional and VAE-guided data augmentations outperforms all the results, thereby demonstrating the goodness of our proposal.},
keywords = {HispaMus},
pubstate = {published},
tppubtype = {inproceedings}
}
Data augmentation is a widely considered technique to improve the performance of Convolutional Neural Networks during training. This step consists in synthetically generate new labeled data by perturbing the samples of the training set, which is expected to provide more robustness to the learning process. The problem is that the augmentation procedure has to be adjusted manually because the perturbations considered must make sense for the task at issue. In this paper we propose the use of Variational Auto-Encoders (VAEs) to generate new synthetic samples, instead of resorting to heuristic strategies. VAEs are powerful generative models that learn a parametric latent space of the input domain from which new samples can be generated. In our experiments over the well-known MNIST dataset, the data augmentation by VAEs improves the base results, yet to a lesser extent of that obtained by a well-adjusted conventional data augmentation. However, the combination of both conventional and VAE-guided data augmentations outperforms all the results, thereby demonstrating the goodness of our proposal. Román, M. A.; Pertusa, A.; Calvo-Zaragoza, J.
A Holistic Approach to Polyphonic Music Transcription with Neural Networks Proceedings Article
In: Flexer, Julián Urbano Geoffroy Peeters Arthur (Ed.): Proc. of the 20th International Society for Music Information Retrieval Conference, ISMIR, pp. 731–737, Delf, The Netherlands, 2019.
@inproceedings{k442,
title = {A Holistic Approach to Polyphonic Music Transcription with Neural Networks},
author = {M. A. Román and A. Pertusa and J. Calvo-Zaragoza},
editor = {Julián Urbano Geoffroy Peeters Arthur Flexer},
year = {2019},
date = {2019-01-01},
booktitle = {Proc. of the 20th International Society for Music Information Retrieval Conference, ISMIR},
pages = {731--737},
address = {Delf, The Netherlands},
keywords = {HispaMus},
pubstate = {published},
tppubtype = {inproceedings}
}
2018
Román, M. A.; Pertusa, A.; Calvo-Zaragoza, J.
An End-to-End Framework for Audio-to-Score Music Transcription on Monophonic Excerpts Proceedings Article
In: Proc. of the 19th International Society for Music Information Retrieval Conference (ISMIR), Paris, France, 2018.
BibTeX | Tags: GRE16-14, HispaMus
@inproceedings{k389,
title = {An End-to-End Framework for Audio-to-Score Music Transcription on Monophonic Excerpts},
author = {M. A. Román and A. Pertusa and J. Calvo-Zaragoza},
year = {2018},
date = {2018-09-01},
urldate = {2018-09-01},
booktitle = {Proc. of the 19th International Society for Music Information Retrieval Conference (ISMIR)},
address = {Paris, France},
keywords = {GRE16-14, HispaMus},
pubstate = {published},
tppubtype = {inproceedings}
}
Calvo-Zaragoza, J.; Rizo, D.
Camera-PrIMuS: Neural End-to-End Optical Music Recognition on Realistic Monophonic Scores Proceedings Article
In: Proceedings of the 19th International Society of Music Information Retrieval (ISMIR), International Society of Music Information Retrieval 2018.
Links | BibTeX | Tags: HispaMus
@inproceedings{k391,
title = {Camera-PrIMuS: Neural End-to-End Optical Music Recognition on Realistic Monophonic Scores},
author = {J. Calvo-Zaragoza and D. Rizo},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/391/33_Paper.pdf},
year = {2018},
date = {2018-09-01},
urldate = {2018-09-01},
booktitle = {Proceedings of the 19th International Society of Music Information Retrieval (ISMIR)},
organization = {International Society of Music Information Retrieval},
keywords = {HispaMus},
pubstate = {published},
tppubtype = {inproceedings}
}
Iñesta, J. M.; León, P. J. Ponce; Rizo, D.; Oncina, J.; Micó, L.; Rico-Juan, J. R.; Pérez-Sancho, C.; Pertusa, A.
HISPAMUS: Handwritten Spanish Music Heritage Preservation by Automatic Transcription Proceedings Article
In: Calvo-Zaragoza, J.; Jr., J. Hajic; Pacha, A. (Ed.): Proceedings of the 1st Workshop on Reading Music Systems, WoRMS, pp. 17–18, Paris, 2018.
Abstract | Links | BibTeX | Tags: HispaMus
@inproceedings{k396,
title = {HISPAMUS: Handwritten Spanish Music Heritage Preservation by Automatic Transcription},
author = {J. M. Iñesta and P. J. Ponce León and D. Rizo and J. Oncina and L. Micó and J. R. Rico-Juan and C. Pérez-Sancho and A. Pertusa},
editor = {J. Calvo-Zaragoza and J. Hajic Jr. and A. Pacha},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/396/worms-2018-inesta.pdf},
year = {2018},
date = {2018-09-01},
urldate = {2018-09-01},
booktitle = {Proceedings of the 1st Workshop on Reading Music Systems, WoRMS},
pages = {17--18},
address = {Paris},
abstract = {The HISPAMUS proposal aims at enhancing the Hispanic music heritage from the 15th to the 19th centuries, by exploiting the digital resources of these collections. In addition, thousands of oral tradition melodies that were compiled by folklorists in the 1950s decade are digitized just as images, currently without the possibility of content-based search or study. It is necessary to develop services and tools for the benefit of archives, libraries, scholars, computer scientists and general public. HISPAMUS tries to provide smart access to archival manuscripts of music scores, allowing its reuse and exploitation. In order to reach this ambitious goal, our group can provide cutting-edge technology in the fields of Machine Learning, Pattern Recognition, and Optical Music Recognition.},
keywords = {HispaMus},
pubstate = {published},
tppubtype = {inproceedings}
}
The HISPAMUS proposal aims at enhancing the Hispanic music heritage from the 15th to the 19th centuries, by exploiting the digital resources of these collections. In addition, thousands of oral tradition melodies that were compiled by folklorists in the 1950s decade are digitized just as images, currently without the possibility of content-based search or study. It is necessary to develop services and tools for the benefit of archives, libraries, scholars, computer scientists and general public. HISPAMUS tries to provide smart access to archival manuscripts of music scores, allowing its reuse and exploitation. In order to reach this ambitious goal, our group can provide cutting-edge technology in the fields of Machine Learning, Pattern Recognition, and Optical Music Recognition. Rizo, D.; Calvo-Zaragoza, J.; Iñesta, J. M.
MuRET: a music recognition, encoding, and transcription tool Proceedings Article
In: Proceedings of the 5th International Conference on Digital Libraries for Musicology (DLfM'18), pp. 52–56, ACM, París, France, 2018, ISBN: 978-1-4503-6522-2.
Abstract | BibTeX | Tags: HispaMus
@inproceedings{k397,
title = {MuRET: a music recognition, encoding, and transcription tool},
author = {D. Rizo and J. Calvo-Zaragoza and J. M. Iñesta},
isbn = {978-1-4503-6522-2},
year = {2018},
date = {2018-09-01},
booktitle = {Proceedings of the 5th International Conference on Digital Libraries for Musicology (DLfM'18)},
pages = {52--56},
publisher = {ACM},
address = {París, France},
abstract = {The transcription process from early and modern notation ma-nu-scripts to a structured digital encoding has been traditionally performed following a fully manual workflow. At most it has received some technological support in particular stages, like optical music recognition (OMR) of the source images, or transcription to modern notation with music edition applications. Currently, there is no mature and stable enough solution for the OMR problem, and the most used music editors do not support early notations, such as the mensural one. In this work, a new tool called MUsic Recognition, Encoding, and Transcription (MuRET) is introduced, which covers all transcription phases, from the manuscript source to the encoded digital content. MuRET is designed as a technology-focused research tool, allowing different processing approaches to be used, and producing both the expected transcribed contents in standard encodings and data for the study of the transcription process itself.},
keywords = {HispaMus},
pubstate = {published},
tppubtype = {inproceedings}
}
The transcription process from early and modern notation ma-nu-scripts to a structured digital encoding has been traditionally performed following a fully manual workflow. At most it has received some technological support in particular stages, like optical music recognition (OMR) of the source images, or transcription to modern notation with music edition applications. Currently, there is no mature and stable enough solution for the OMR problem, and the most used music editors do not support early notations, such as the mensural one. In this work, a new tool called MUsic Recognition, Encoding, and Transcription (MuRET) is introduced, which covers all transcription phases, from the manuscript source to the encoded digital content. MuRET is designed as a technology-focused research tool, allowing different processing approaches to be used, and producing both the expected transcribed contents in standard encodings and data for the study of the transcription process itself. Castellanos, F. J.; Calvo-Zaragoza, J.; Vigliensoni, G.; Fujinaga, I.
Document Analysis of Music Score Images with Selectional Auto-Encoders Proceedings Article
In: Proceedings of the19th International Society for Music Information Retrieval Conference, pp. 256-263, ISMIR 2018 Paris, France, 2018.
@inproceedings{k449,
title = {Document Analysis of Music Score Images with Selectional Auto-Encoders},
author = {F. J. Castellanos and J. Calvo-Zaragoza and G. Vigliensoni and I. Fujinaga},
year = {2018},
date = {2018-09-01},
booktitle = {Proceedings of the19th International Society for Music Information Retrieval Conference},
pages = {256-263},
address = {Paris, France},
organization = {ISMIR 2018},
keywords = {HispaMus},
pubstate = {published},
tppubtype = {inproceedings}
}
Calvo-Zaragoza, J.; Rizo, D.
End-to-End Neural Optical Music Recognition of Monophonic Scores Journal Article
In: Applied Sciences, vol. 8, no. 4, pp. 606–623, 2018, ISSN: 2076-3417.
@article{k390,
title = {End-to-End Neural Optical Music Recognition of Monophonic Scores},
author = {J. Calvo-Zaragoza and D. Rizo},
issn = {2076-3417},
year = {2018},
date = {2018-04-01},
journal = {Applied Sciences},
volume = {8},
number = {4},
pages = {606--623},
keywords = {HispaMus},
pubstate = {published},
tppubtype = {article}
}
Gallego, A. J.; Pertusa, A.; Calvo-Zaragoza, J.
Improving Convolutional Neural Networks’ Accuracy in Noisy Environments Using k-Nearest Neighbors Journal Article
In: Applied Sciences, vol. 8, no. 11, 2018, ISSN: 2076-3417.
Abstract | BibTeX | Tags: HispaMus
@article{k399,
title = {Improving Convolutional Neural Networks’ Accuracy in Noisy Environments Using k-Nearest Neighbors},
author = {A. J. Gallego and A. Pertusa and J. Calvo-Zaragoza},
issn = {2076-3417},
year = {2018},
date = {2018-01-01},
journal = {Applied Sciences},
volume = {8},
number = {11},
abstract = {We present a hybrid approach to improve the accuracy of Convolutional Neural Networks (CNN) without retraining the model. The proposed architecture replaces the softmax layer by a k-Nearest Neighbor (kNN) algorithm for inference. Although this is a common technique in transfer learning, we apply it to the same domain for which the network was trained. Previous works show that neural codes (neuron activations of the last hidden layers) can benefit from the inclusion of classifiers such as support vector machines or random forests. In this work, our proposed hybrid CNN + kNN architecture is evaluated using several image datasets, network topologies and label noise levels. The results show significant accuracy improvements in the inference stage with respect to the standard CNN with noisy labels, especially with relatively large datasets such as CIFAR100. We also verify that applying the ℓ and 2
norm on neural codes is statistically beneficial for this approach.},
keywords = {HispaMus},
pubstate = {published},
tppubtype = {article}
}
We present a hybrid approach to improve the accuracy of Convolutional Neural Networks (CNN) without retraining the model. The proposed architecture replaces the softmax layer by a k-Nearest Neighbor (kNN) algorithm for inference. Although this is a common technique in transfer learning, we apply it to the same domain for which the network was trained. Previous works show that neural codes (neuron activations of the last hidden layers) can benefit from the inclusion of classifiers such as support vector machines or random forests. In this work, our proposed hybrid CNN + kNN architecture is evaluated using several image datasets, network topologies and label noise levels. The results show significant accuracy improvements in the inference stage with respect to the standard CNN with noisy labels, especially with relatively large datasets such as CIFAR100. We also verify that applying the ℓ and 2
norm on neural codes is statistically beneficial for this approach. Sober-Mira, J.; Calvo-Zaragoza, J.; Rizo, D.; Iñesta, J. M.
Pen-Based Music Document Transcription with Convolutional Neural Networks Book Chapter
In: Fornés, A.; Lamiroy, B. (Ed.): Graphics Recognition. Current Trends and Evolutions, Chapter 6, pp. 71–80, Springer, 2018, ISBN: 978-3-030-02284-6.
Abstract | BibTeX | Tags: HispaMus
@inbook{k400,
title = {Pen-Based Music Document Transcription with Convolutional Neural Networks},
author = {J. Sober-Mira and J. Calvo-Zaragoza and D. Rizo and J. M. Iñesta},
editor = {A. Fornés and B. Lamiroy},
isbn = {978-3-030-02284-6},
year = {2018},
date = {2018-01-01},
booktitle = {Graphics Recognition. Current Trends and Evolutions},
pages = {71--80},
publisher = {Springer},
chapter = {6},
abstract = {The transcription of music sources requires new ways of interacting with musical documents. Assuming that au- tomatic technologies will never guarantee a perfect transcription, our intention is to develop an interactive system in which user and software collaborate to complete the task. Since the use of traditional software for score edition might be tedious, our work studies the interaction by means of electronic pen (e-pen). In our framework, users trace symbols using an e-pen over a digital surface, which provides both the underlying image (offline data) and the drawing made (online data). Using both sources, the system is capable of reaching an error below 4% when recognizing the symbols with a Convolutional Neural Network.},
keywords = {HispaMus},
pubstate = {published},
tppubtype = {inbook}
}
The transcription of music sources requires new ways of interacting with musical documents. Assuming that au- tomatic technologies will never guarantee a perfect transcription, our intention is to develop an interactive system in which user and software collaborate to complete the task. Since the use of traditional software for score edition might be tedious, our work studies the interaction by means of electronic pen (e-pen). In our framework, users trace symbols using an e-pen over a digital surface, which provides both the underlying image (offline data) and the drawing made (online data). Using both sources, the system is capable of reaching an error below 4% when recognizing the symbols with a Convolutional Neural Network. Calvo-Zaragoza, J.; Castellanos, F. J.; Vigliensoni, G.; Fujinaga, I.
Deep Neural Networks for Document Processing of Music Score Images Journal Article
In: Applied Sciences, vol. 8, no. 5, pp. 654, 2018.
@article{k427,
title = {Deep Neural Networks for Document Processing of Music Score Images},
author = {J. Calvo-Zaragoza and F. J. Castellanos and G. Vigliensoni and I. Fujinaga},
year = {2018},
date = {2018-01-01},
urldate = {2018-01-01},
journal = {Applied Sciences},
volume = {8},
number = {5},
pages = {654},
keywords = {HispaMus},
pubstate = {published},
tppubtype = {article}
}
2021
Castellanos, F. J.; Gallego, A. J.; Calvo-Zaragoza, J.
Unsupervised Neural Domain Adaptation for Document Image Binarization Journal Article
In: Pattern Recognition, vol. 119, pp. 108099, 2021.
BibTeX | Tags: GRE19-04, HispaMus
@article{k467,
title = {Unsupervised Neural Domain Adaptation for Document Image Binarization},
author = {F. J. Castellanos and A. J. Gallego and J. Calvo-Zaragoza},
year = {2021},
date = {2021-11-01},
urldate = {2021-11-01},
journal = {Pattern Recognition},
volume = {119},
pages = {108099},
keywords = {GRE19-04, HispaMus},
pubstate = {published},
tppubtype = {article}
}
Gallego, A. J.; Calvo-Zaragoza, J.; Fisher, R. B.
Incremental Unsupervised Domain-Adversarial Training of Neural Networks Journal Article
In: IEEE Transactions on Neural Networks and Learning Systems, vol. 32, no. 11, pp. 4864-4878, 2021, ISSN: 2162-2388.
Abstract | Links | BibTeX | Tags: GRE19-04, HispaMus
@article{k455,
title = {Incremental Unsupervised Domain-Adversarial Training of Neural Networks},
author = {A. J. Gallego and J. Calvo-Zaragoza and R. B. Fisher},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/455/2001.04129.pdf},
issn = {2162-2388},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
journal = {IEEE Transactions on Neural Networks and Learning Systems},
volume = {32},
number = {11},
pages = {4864-4878},
abstract = {In the context of supervised statistical learning, it is typically assumed that the training set comes from the same distribution that draws the test samples. When this is not the case, the behavior of the learned model is unpredictable and becomes dependent upon the degree of similarity between the distribution of the training set and the distribution of the test set. One of the research topics that investigates this scenario is referred to as Domain Adaptation (DA). Deep neural networks brought dramatic advances in pattern recognition and that is why there have been many attempts to provide good domain adaptation algorithms for these models. Here we take a different avenue and approach the problem from an incremental point of view, where the model is adapted to the new domain iteratively. We make use of an existing unsupervised domain-adaptation algorithm to identify the target samples on which there is greater confidence about their true label. The output of the model is analyzed in different ways to determine the candidate samples. The selected samples are then added to the source training set by self-labeling, and the process is repeated until all target samples are labeled. This approach implements a form of adversarial training in which, by moving the self-labeled samples from the target to the source set, the DA algorithm is forced to look for new features after each iteration. Our results report a clear improvement with respect to the non-incremental case in several datasets, also outperforming other state-of-the-art domain adaptation algorithms.},
keywords = {GRE19-04, HispaMus},
pubstate = {published},
tppubtype = {article}
}
Román, M. A.
An End-to-End Framework for Audio-to-Score Music Transcription PhD Thesis
2021.
@phdthesis{k462,
title = {An End-to-End Framework for Audio-to-Score Music Transcription},
author = {M. A. Román},
editor = {J. Calvo-Zaragoza and A. Pertusa},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
organization = {Universidad de Alicante},
keywords = {HispaMus},
pubstate = {published},
tppubtype = {phdthesis}
}
Calvo-Zaragoza, J.; Rizo, D.; Iñesta, J. M.
Reconocimiento Óptico de Partituras (OMR) aplicado al Fonde de Música Tradicional IMF-CSIC Book Chapter
In: Gambero-Ustárroz, M.; Ros-Fábregas, E. (Ed.): Musicología en Web. Patrimonio musical y Humanidades Digitales, Chapter 4, pp. 87-109, Edition Reichenberger, 2021, ISBN: 978-3-967280-14-2.
@inbook{k470,
title = {Reconocimiento Óptico de Partituras (OMR) aplicado al Fonde de Música Tradicional IMF-CSIC},
author = {J. Calvo-Zaragoza and D. Rizo and J. M. Iñesta},
editor = {M. Gambero-Ustárroz and E. Ros-Fábregas},
isbn = {978-3-967280-14-2},
year = {2021},
date = {2021-01-01},
booktitle = {Musicología en Web. Patrimonio musical y Humanidades Digitales},
pages = {87-109},
publisher = {Edition Reichenberger},
chapter = {4},
keywords = {HispaMus},
pubstate = {published},
tppubtype = {inbook}
}
Castellanos, F. J.; Valero-Mas, J. J.; Calvo-Zaragoza, J.
Prototype Generation in the String Space via Approximate Median for Data Reduction in Nearest Neighbor classification Journal Article
In: Soft Computing, vol. 25, 2021, ISSN: 15403-15415.
BibTeX | Tags: GRE19-04, HispaMus
@article{k476,
title = {Prototype Generation in the String Space via Approximate Median for Data Reduction in Nearest Neighbor classification},
author = {F. J. Castellanos and J. J. Valero-Mas and J. Calvo-Zaragoza},
issn = {15403-15415},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
journal = {Soft Computing},
volume = {25},
keywords = {GRE19-04, HispaMus},
pubstate = {published},
tppubtype = {article}
}
2020
Ríos-Vila, A.; Calvo-Zaragoza, J.; Rizo, D.
Evaluating Simultaneous Recognition and Encoding for Optical Music Recognition Proceedings Article
In: DLfM 2020: 7th International Conference on Digital Libraries for Musicology, pp. 10-17, Association for Computing Machinery, 2020, ISBN: 978-1-4503-8760-6.
@inproceedings{k456,
title = {Evaluating Simultaneous Recognition and Encoding for Optical Music Recognition},
author = {A. Ríos-Vila and J. Calvo-Zaragoza and D. Rizo},
isbn = {978-1-4503-8760-6},
year = {2020},
date = {2020-10-01},
booktitle = {DLfM 2020: 7th International Conference on Digital Libraries for Musicology},
journal = {DLfM 2020: 7th International Conference on Digital Libraries for Musicology},
pages = {10-17},
publisher = {Association for Computing Machinery},
keywords = {HispaMus},
pubstate = {published},
tppubtype = {inproceedings}
}
Castellanos, F. J.; Calvo-Zaragoza, J.; Iñesta, J. M.
A neural approach for full-page Optical Music Recognition of mensural documents Proceedings Article
In: Proceedings of the 21st International Society for Music Information Retrieval Conference, pp. 558-565, Montréal, Canada, 2020, ISBN: 978-0-9813537-0-8.
@inproceedings{k457,
title = {A neural approach for full-page Optical Music Recognition of mensural documents},
author = {F. J. Castellanos and J. Calvo-Zaragoza and J. M. Iñesta},
isbn = {978-0-9813537-0-8},
year = {2020},
date = {2020-10-01},
booktitle = {Proceedings of the 21st International Society for Music Information Retrieval Conference},
pages = {558-565},
address = {Montréal, Canada},
keywords = {HispaMus},
pubstate = {published},
tppubtype = {inproceedings}
}
Castellanos, F. J.; Calvo-Zaragoza, J.; Iñesta, J. M.
Two-step neural cross-domain experiments forfull-page recognition of Mensural documents Proceedings Article
In: Proc. of the 13th International Workshop on Machine Learning and Music, pp. 56–60, MML 2020 13th International Workshop on Machine Learning and Music, 2020.
BibTeX | Tags: GRE19-04, HispaMus
@inproceedings{k448,
title = {Two-step neural cross-domain experiments forfull-page recognition of Mensural documents},
author = {F. J. Castellanos and J. Calvo-Zaragoza and J. M. Iñesta},
year = {2020},
date = {2020-09-01},
booktitle = {Proc. of the 13th International Workshop on Machine Learning and Music},
pages = {56--60},
publisher = {13th International Workshop on Machine Learning and Music},
organization = {MML 2020},
keywords = {GRE19-04, HispaMus},
pubstate = {published},
tppubtype = {inproceedings}
}
Thomae, M. E.; Ríos-Vila, A.; Calvo-Zaragoza, J.; Rizo, D.; Iñesta, J. M.
Retrieving Music Semantics from Optical Music Recognition by Machine Translation Proceedings Article
In: Luca, Elsa De; Flanders, Julia (Ed.): Music Encoding Conference Proceedings 26-29 May, 2020 Tufts University, Boston (USA), pp. 19-24, Music Encoding Initiative 2020.
Links | BibTeX | Tags: HispaMus
@inproceedings{k446,
title = {Retrieving Music Semantics from Optical Music Recognition by Machine Translation},
author = {M. E. Thomae and A. Ríos-Vila and J. Calvo-Zaragoza and D. Rizo and J. M. Iñesta},
editor = {Elsa De Luca and Julia Flanders},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/446/music_encoding_conference_proceedings_2020.pdf},
year = {2020},
date = {2020-05-01},
booktitle = {Music Encoding Conference Proceedings 26-29 May, 2020 Tufts University, Boston (USA)},
pages = {19-24},
organization = {Music Encoding Initiative},
keywords = {HispaMus},
pubstate = {published},
tppubtype = {inproceedings}
}
Calvo-Zaragoza, J.; Jr., J. Hajic; Pacha, A.
Understanding Optical Music Recognition Journal Article
In: ACM Computing Surveys, vol. 53, no. 4, pp. 77, 2020.
@article{k426,
title = {Understanding Optical Music Recognition},
author = {J. Calvo-Zaragoza and J. Hajic Jr. and A. Pacha},
year = {2020},
date = {2020-01-01},
journal = {ACM Computing Surveys},
volume = {53},
number = {4},
pages = {77},
keywords = {HispaMus},
pubstate = {published},
tppubtype = {article}
}
Gallego, A. J.; Calvo-Zaragoza, J.; Rico-Juan, J. R.
Insights Into Efficient k-Nearest Neighbor Classification With Convolutional Neural Codes Journal Article
In: IEEE Access, vol. 8, pp. 99312-99326, 2020, ISSN: 2169-3536.
Abstract | BibTeX | Tags: HispaMus
@article{k444,
title = {Insights Into Efficient k-Nearest Neighbor Classification With Convolutional Neural Codes},
author = {A. J. Gallego and J. Calvo-Zaragoza and J. R. Rico-Juan},
issn = {2169-3536},
year = {2020},
date = {2020-01-01},
urldate = {2020-01-01},
journal = {IEEE Access},
volume = {8},
pages = {99312-99326},
abstract = {The increasing consideration of Convolutional Neural Networks (CNN) has not prevented the use of the k-Nearest Neighbor (kNN) method. In fact, a hybrid CNN-kNN approach is an interesting option in which the network specializes in feature extraction through its activations (Neural Codes), while the kNN has the advantage of performing a retrieval by means of similarity. However, this hybrid approach also has the disadvantages of the kNN search, and especially its high computational cost which is, in principle, undesirable for large-scale data. In this paper, we present the first comprehensive study of efficient kNN search algorithms using this hybrid CNN-kNN approach. This has been done by considering up to 16 different algorithms, each of which is evaluated with a different parametrization, in 7 datasets of heterogeneous composition. Our results show that no single algorithm is capable of covering all aspects, but rather that each family of algorithms is better suited to specific aspects of the problem. This signifies that Fast Similarity Search algorithms maintain their performance, but do not reduce the cost as much as the Data Reduction family does. In turn, the Approximated Similarity Search family is postulated as a good option when attempting to balance accuracy and efficiency. The experiments also suggest that considering statistical transformation algorithms such as Linear Discriminant Analysis might be useful in certain cases.},
keywords = {HispaMus},
pubstate = {published},
tppubtype = {article}
}
Ríos-Vila, A.; Calvo-Zaragoza, J.; Iñesta, J. M.
Exploring the two-dimensional nature of music notation for score recognition with end-to-end approaches Proceedings Article
In: Proc. of 17th International Conference on Frontiers in Handwriting Recognition (ICFHR), pp. 193–198, IEEE Computer Society IEEE, Dormund (Germany), 2020, ISBN: 978-1-7281-9966-5.
Abstract | BibTeX | Tags: HispaMus
@inproceedings{k461,
title = {Exploring the two-dimensional nature of music notation for score recognition with end-to-end approaches},
author = {A. Ríos-Vila and J. Calvo-Zaragoza and J. M. Iñesta},
isbn = {978-1-7281-9966-5},
year = {2020},
date = {2020-01-01},
booktitle = {Proc. of 17th International Conference on Frontiers in Handwriting Recognition (ICFHR)},
pages = {193--198},
publisher = {IEEE},
address = {Dormund (Germany)},
organization = {IEEE Computer Society},
abstract = {Optical Music Recognition workflows perform several steps to retrieve the content in music score images, being symbol recognition one of the key stages. State-of-the-art approaches for this stage currently address the coding of the output symbols as if they were plain text characters. However, music symbols have a two-dimensional nature that is ignored in these approaches. In this paper, we explore alternative output representations to perform music symbol recognition with state-of-the-art end-to-end neural technologies. We propose and describe new output representations which take into account the mentioned two-dimensional nature. We seek answers to the question of whether it is possible to obtain better recognition results in both printed and handwritten music scores. In this analysis, we compare the results given using three output encodings and two neural approaches. We found that one of the proposed encodings outperforms the results obtained by the standard one. This permits us to conclude that it is interesting to keep researching on this topic to improve end-to-end music score recognition.},
keywords = {HispaMus},
pubstate = {published},
tppubtype = {inproceedings}
}
Rizo, D.; Calvo-Zaragoza, J.; Iñesta, J. M.
Preservación del patrimonio musical mediante transcripción asistida por ordenador Book Chapter
In: Isusi-Fagoaga, R.; Serrano, F. Villanueva (Ed.): La música de la Corona d’Aragó: investigació, transferència i educació, Chapter 15, pp. 275–298, Universitat de València, 2020, ISBN: 978-84-09-19985-3.
@inbook{k466,
title = {Preservación del patrimonio musical mediante transcripción asistida por ordenador},
author = {D. Rizo and J. Calvo-Zaragoza and J. M. Iñesta},
editor = {R. Isusi-Fagoaga and F. Villanueva Serrano},
isbn = {978-84-09-19985-3},
year = {2020},
date = {2020-01-01},
urldate = {2020-01-01},
booktitle = {La música de la Corona d’Aragó: investigació, transferència i educació},
pages = {275--298},
publisher = {Universitat de València},
chapter = {15},
keywords = {HispaMus},
pubstate = {published},
tppubtype = {inbook}
}
2019
Calvo-Zaragoza, J.; Toselli, A. H.; Vidal, E.
Handwritten Music Recognition for Mensural Notation with Convolutional Recurrent Neural Networks Journal Article
In: Pattern Recognition Letters, vol. 128, pp. 115–121, 2019.
Links | BibTeX | Tags: HispaMus
@article{k415,
title = {Handwritten Music Recognition for Mensural Notation with Convolutional Recurrent Neural Networks},
author = {J. Calvo-Zaragoza and A. H. Toselli and E. Vidal},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/415/1-s2.0-S0167865519302338-main.pdf},
year = {2019},
date = {2019-12-01},
journal = {Pattern Recognition Letters},
volume = {128},
pages = {115--121},
keywords = {HispaMus},
pubstate = {published},
tppubtype = {article}
}
Iñesta, J. M.; Rizo, D.; Calvo-Zaragoza, J.
MuRET as a software for the transcription of historical archives Proceedings Article
In: Proceedings of the 2nd Workshop on Reading Music Systems, WoRMS, pp. 12–15, Delft (The Nederlands), 2019.
Abstract | Links | BibTeX | Tags: HispaMus
@inproceedings{k437,
title = {MuRET as a software for the transcription of historical archives},
author = {J. M. Iñesta and D. Rizo and J. Calvo-Zaragoza},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/437/worms-2019-inesta.pdf},
year = {2019},
date = {2019-11-01},
booktitle = {Proceedings of the 2nd Workshop on Reading Music Systems, WoRMS},
pages = {12--15},
address = {Delft (The Nederlands)},
abstract = {The transcription process from historical hand- written music manuscripts to a structured digital encoding has been traditionally performed following a fully manual workflow. At most, it has received some technological support in particular stages, like optical music recognition (OMR) of the source images, or transcription to modern notation with music edition applications. Currently, there is no mature and stable enough solution for the OMR problem, and the most used music editors do not support early notations, such as the mensural notation. A new tool called MUsic Recognition, Encoding, and Transcription (MuRET) has been developed, which covers all transcription phases, from the manuscript image to the encoded digital content. MuRET is designed as a machine-learning based research tool, allowing different processing approaches to be used, and producing both the expected transcribed contents in standard encodings and data for the study of the transcription process.},
keywords = {HispaMus},
pubstate = {published},
tppubtype = {inproceedings}
}
Ríos-Vila, A.; Calvo-Zaragoza, J.; Rizo, D.; Iñesta, J. M.
ReadSco: An Open-Source Web-Based Optical Music Recognition Tool Proceedings Article
In: Calvo-Zaragoza, J.; Pacha, A. (Ed.): Proc. of the 2nd International Workshop on Reading Music Systems, WoRMS 2019, pp. 27-30, Delft (The Netherlands), 2019.
Abstract | Links | BibTeX | Tags: HispaMus
@inproceedings{k439,
title = {ReadSco: An Open-Source Web-Based Optical Music Recognition Tool},
author = {A. Ríos-Vila and J. Calvo-Zaragoza and D. Rizo and J. M. Iñesta},
editor = {J. Calvo-Zaragoza and A. Pacha},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/439/ReadSco_Worms2019.pdf},
year = {2019},
date = {2019-11-01},
urldate = {2019-11-01},
booktitle = {Proc. of the 2nd International Workshop on Reading Music Systems, WoRMS 2019},
pages = {27-30},
address = {Delft (The Netherlands)},
abstract = {We introduce READSCO, an open-source web-based community tool for Optical Music Recognition. READSCO aims to serve as a connection between research results and practical use. We describe the design decisions considered to both favours a rapid integration of new advances from the research field and
facilitate the community’s participation in its development. The project is still in its planning phase, so this work is a good opportunity to present the main idea and get direct feedback from other researchers.},
keywords = {HispaMus},
pubstate = {published},
tppubtype = {inproceedings}
}
facilitate the community’s participation in its development. The project is still in its planning phase, so this work is a good opportunity to present the main idea and get direct feedback from other researchers.
Iñesta, J. M.; Rizo, D.; Calvo-Zaragoza, J.
Recognition, encoding, and transcription of early mensural handwritten music Proceedings Article
In: procedings of the 13th International Workshop on Graphics Recognition (GREC 2019), pp. 13-14, Sydney (Australia), 2019.
@inproceedings{k416,
title = {Recognition, encoding, and transcription of early mensural handwritten music},
author = {J. M. Iñesta and D. Rizo and J. Calvo-Zaragoza},
year = {2019},
date = {2019-09-01},
booktitle = {procedings of the 13th International Workshop on Graphics Recognition (GREC 2019)},
pages = {13-14},
address = {Sydney (Australia)},
keywords = {HispaMus},
pubstate = {published},
tppubtype = {inproceedings}
}
Alfaro-Contreras, M.; Calvo-Zaragoza, J.; Iñesta, J. M.
Approaching End-to-end Optical Music Recognition for Homophonic Scores Proceedings Article
In: Iberian Conference on Pattern Recognition and Image Analysis, IbPRIA 2019, pp. 147–158, Springer, Madrid, 2019, ISBN: 978-3-030-31321-0.
Links | BibTeX | Tags: HispaMus
@inproceedings{k419,
title = {Approaching End-to-end Optical Music Recognition for Homophonic Scores},
author = {M. Alfaro-Contreras and J. Calvo-Zaragoza and J. M. Iñesta},
url = {https://link.springer.com/chapter/10.1007/978-3-030-31321-0_13},
isbn = {978-3-030-31321-0},
year = {2019},
date = {2019-08-01},
urldate = {2019-08-01},
booktitle = {Iberian Conference on Pattern Recognition and Image Analysis, IbPRIA 2019},
pages = {147--158},
publisher = {Springer},
address = {Madrid},
keywords = {HispaMus},
pubstate = {published},
tppubtype = {inproceedings}
}
Mateiu, T. N.; Gallego, A. J.; Calvo-Zaragoza, J.
Domain Adaptation for Handwritten Symbol Recognition: A Case of Study in Old Music Manuscripts Proceedings Article
In: Iberian Conference on Pattern Recognition and Image Analysis, IbPRIA, pp. 135–146, Springer International Publishing, Madrid, Spain, 2019, ISBN: 978-3-030-31321-0.
Abstract | BibTeX | Tags: HispaMus
@inproceedings{k410,
title = {Domain Adaptation for Handwritten Symbol Recognition: A Case of Study in Old Music Manuscripts},
author = {T. N. Mateiu and A. J. Gallego and J. Calvo-Zaragoza},
isbn = {978-3-030-31321-0},
year = {2019},
date = {2019-07-01},
urldate = {2019-07-01},
booktitle = {Iberian Conference on Pattern Recognition and Image Analysis, IbPRIA},
pages = {135--146},
publisher = {Springer International Publishing},
address = {Madrid, Spain},
abstract = {The existence of a large amount of untranscripted music manuscripts has caused initiatives that use Machine Learning (ML) for Optical Music Recognition, in order to efficiently transcribe the music sources into a machine-readable format. Although most music manuscript are similar in nature, they inevitably vary from one another. This fact can negatively influence the complexity of the classification task because most ML models fail to transfer their knowledge from one domain to another, thereby requiring learning from scratch on new domains after manually labeling new data. This work studies the ability of a Domain Adversarial Neural Network for domain adaptation in the context of classifying handwritten music symbols. The main idea is to exploit the knowledge of a specific manuscript to classify symbols from different (unlabeled) manuscripts. The reported results are promising, obtaining a substantial improvement over a conventional Convolutional Neural Network approach, which can be used as a basis for future research.},
keywords = {HispaMus},
pubstate = {published},
tppubtype = {inproceedings}
}
Nuñez-Alcover, Alicia; León, P. J. Ponce; Calvo-Zaragoza, J.
Glyph and Position Classification of Music Symbols in Early Music Manuscripts Proceedings Article
In: Morales, A.; Fierrez, J.; Sánchez, J. Salvador; Ribeiro, B. (Ed.): Proc. of the 9th Iberian Conference on Pattern Recognition and Image Analysis, LNCS vol. 11867, pp. 159-168, AERFAI, APRP Springer, Madrid, Spain, 2019, ISBN: 978-3-030-31331-9.
Abstract | Links | BibTeX | Tags: HispaMus
@inproceedings{k420,
title = {Glyph and Position Classification of Music Symbols in Early Music Manuscripts},
author = {Alicia Nuñez-Alcover and P. J. Ponce León and J. Calvo-Zaragoza},
editor = {A. Morales and J. Fierrez and J. Salvador Sánchez and B. Ribeiro},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/420/IbPRIA2019_paper_91-1.pdf},
isbn = {978-3-030-31331-9},
year = {2019},
date = {2019-07-01},
booktitle = {Proc. of the 9th Iberian Conference on Pattern Recognition and Image Analysis, LNCS vol. 11867},
pages = {159-168},
publisher = {Springer},
address = {Madrid, Spain},
organization = {AERFAI, APRP},
abstract = {Optical Music Recognition is a field of research that automates the reading of musical scores so as to transcribe their content into a structured digital format. When dealing with music manuscripts, the traditional workflow establishes separate stages of detection and classification of musical symbols. In the latter, most of the research has focused on detecting musical glyphs, ignoring that the meaning of a musical symbol is defined by two components: its glyph and its position within the staff. In this paper we study how to perform both glyph and position classification of handwritten musical symbols in early music manuscripts written in white Mensural notation, a common notation system used for the most part of the XVI and XVII centuries. We make use of Convolutional Neural Networks as the classification method, and we tested several alternatives such as using independent models for each component, combining label spaces, or using both multi-input and multi-output models. Our results on early music manuscripts provide insights about the effectiveness and efficiency of each approach.},
keywords = {HispaMus},
pubstate = {published},
tppubtype = {inproceedings}
}
Garay-Maestre, U.; Gallego, A. J.; Calvo-Zaragoza, J.
Data Augmentation via Variational Auto-Encoders Proceedings Article
In: Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications, pp. 29–37, 2019, ISBN: 978-3-030-13469-3.
Abstract | BibTeX | Tags: HispaMus
@inproceedings{k406,
title = {Data Augmentation via Variational Auto-Encoders},
author = {U. Garay-Maestre and A. J. Gallego and J. Calvo-Zaragoza},
isbn = {978-3-030-13469-3},
year = {2019},
date = {2019-01-01},
urldate = {2019-01-01},
booktitle = {Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications},
pages = {29--37},
abstract = {Data augmentation is a widely considered technique to improve the performance of Convolutional Neural Networks during training. This step consists in synthetically generate new labeled data by perturbing the samples of the training set, which is expected to provide more robustness to the learning process. The problem is that the augmentation procedure has to be adjusted manually because the perturbations considered must make sense for the task at issue. In this paper we propose the use of Variational Auto-Encoders (VAEs) to generate new synthetic samples, instead of resorting to heuristic strategies. VAEs are powerful generative models that learn a parametric latent space of the input domain from which new samples can be generated. In our experiments over the well-known MNIST dataset, the data augmentation by VAEs improves the base results, yet to a lesser extent of that obtained by a well-adjusted conventional data augmentation. However, the combination of both conventional and VAE-guided data augmentations outperforms all the results, thereby demonstrating the goodness of our proposal.},
keywords = {HispaMus},
pubstate = {published},
tppubtype = {inproceedings}
}
Román, M. A.; Pertusa, A.; Calvo-Zaragoza, J.
A Holistic Approach to Polyphonic Music Transcription with Neural Networks Proceedings Article
In: Flexer, Julián Urbano Geoffroy Peeters Arthur (Ed.): Proc. of the 20th International Society for Music Information Retrieval Conference, ISMIR, pp. 731–737, Delf, The Netherlands, 2019.
@inproceedings{k442,
title = {A Holistic Approach to Polyphonic Music Transcription with Neural Networks},
author = {M. A. Román and A. Pertusa and J. Calvo-Zaragoza},
editor = {Julián Urbano Geoffroy Peeters Arthur Flexer},
year = {2019},
date = {2019-01-01},
booktitle = {Proc. of the 20th International Society for Music Information Retrieval Conference, ISMIR},
pages = {731--737},
address = {Delf, The Netherlands},
keywords = {HispaMus},
pubstate = {published},
tppubtype = {inproceedings}
}
2018
Román, M. A.; Pertusa, A.; Calvo-Zaragoza, J.
An End-to-End Framework for Audio-to-Score Music Transcription on Monophonic Excerpts Proceedings Article
In: Proc. of the 19th International Society for Music Information Retrieval Conference (ISMIR), Paris, France, 2018.
BibTeX | Tags: GRE16-14, HispaMus
@inproceedings{k389,
title = {An End-to-End Framework for Audio-to-Score Music Transcription on Monophonic Excerpts},
author = {M. A. Román and A. Pertusa and J. Calvo-Zaragoza},
year = {2018},
date = {2018-09-01},
urldate = {2018-09-01},
booktitle = {Proc. of the 19th International Society for Music Information Retrieval Conference (ISMIR)},
address = {Paris, France},
keywords = {GRE16-14, HispaMus},
pubstate = {published},
tppubtype = {inproceedings}
}
Calvo-Zaragoza, J.; Rizo, D.
Camera-PrIMuS: Neural End-to-End Optical Music Recognition on Realistic Monophonic Scores Proceedings Article
In: Proceedings of the 19th International Society of Music Information Retrieval (ISMIR), International Society of Music Information Retrieval 2018.
Links | BibTeX | Tags: HispaMus
@inproceedings{k391,
title = {Camera-PrIMuS: Neural End-to-End Optical Music Recognition on Realistic Monophonic Scores},
author = {J. Calvo-Zaragoza and D. Rizo},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/391/33_Paper.pdf},
year = {2018},
date = {2018-09-01},
urldate = {2018-09-01},
booktitle = {Proceedings of the 19th International Society of Music Information Retrieval (ISMIR)},
organization = {International Society of Music Information Retrieval},
keywords = {HispaMus},
pubstate = {published},
tppubtype = {inproceedings}
}
Iñesta, J. M.; León, P. J. Ponce; Rizo, D.; Oncina, J.; Micó, L.; Rico-Juan, J. R.; Pérez-Sancho, C.; Pertusa, A.
HISPAMUS: Handwritten Spanish Music Heritage Preservation by Automatic Transcription Proceedings Article
In: Calvo-Zaragoza, J.; Jr., J. Hajic; Pacha, A. (Ed.): Proceedings of the 1st Workshop on Reading Music Systems, WoRMS, pp. 17–18, Paris, 2018.
Abstract | Links | BibTeX | Tags: HispaMus
@inproceedings{k396,
title = {HISPAMUS: Handwritten Spanish Music Heritage Preservation by Automatic Transcription},
author = {J. M. Iñesta and P. J. Ponce León and D. Rizo and J. Oncina and L. Micó and J. R. Rico-Juan and C. Pérez-Sancho and A. Pertusa},
editor = {J. Calvo-Zaragoza and J. Hajic Jr. and A. Pacha},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/396/worms-2018-inesta.pdf},
year = {2018},
date = {2018-09-01},
urldate = {2018-09-01},
booktitle = {Proceedings of the 1st Workshop on Reading Music Systems, WoRMS},
pages = {17--18},
address = {Paris},
abstract = {The HISPAMUS proposal aims at enhancing the Hispanic music heritage from the 15th to the 19th centuries, by exploiting the digital resources of these collections. In addition, thousands of oral tradition melodies that were compiled by folklorists in the 1950s decade are digitized just as images, currently without the possibility of content-based search or study. It is necessary to develop services and tools for the benefit of archives, libraries, scholars, computer scientists and general public. HISPAMUS tries to provide smart access to archival manuscripts of music scores, allowing its reuse and exploitation. In order to reach this ambitious goal, our group can provide cutting-edge technology in the fields of Machine Learning, Pattern Recognition, and Optical Music Recognition.},
keywords = {HispaMus},
pubstate = {published},
tppubtype = {inproceedings}
}
Rizo, D.; Calvo-Zaragoza, J.; Iñesta, J. M.
MuRET: a music recognition, encoding, and transcription tool Proceedings Article
In: Proceedings of the 5th International Conference on Digital Libraries for Musicology (DLfM'18), pp. 52–56, ACM, París, France, 2018, ISBN: 978-1-4503-6522-2.
Abstract | BibTeX | Tags: HispaMus
@inproceedings{k397,
title = {MuRET: a music recognition, encoding, and transcription tool},
author = {D. Rizo and J. Calvo-Zaragoza and J. M. Iñesta},
isbn = {978-1-4503-6522-2},
year = {2018},
date = {2018-09-01},
booktitle = {Proceedings of the 5th International Conference on Digital Libraries for Musicology (DLfM'18)},
pages = {52--56},
publisher = {ACM},
address = {París, France},
abstract = {The transcription process from early and modern notation ma-nu-scripts to a structured digital encoding has been traditionally performed following a fully manual workflow. At most it has received some technological support in particular stages, like optical music recognition (OMR) of the source images, or transcription to modern notation with music edition applications. Currently, there is no mature and stable enough solution for the OMR problem, and the most used music editors do not support early notations, such as the mensural one. In this work, a new tool called MUsic Recognition, Encoding, and Transcription (MuRET) is introduced, which covers all transcription phases, from the manuscript source to the encoded digital content. MuRET is designed as a technology-focused research tool, allowing different processing approaches to be used, and producing both the expected transcribed contents in standard encodings and data for the study of the transcription process itself.},
keywords = {HispaMus},
pubstate = {published},
tppubtype = {inproceedings}
}
Castellanos, F. J.; Calvo-Zaragoza, J.; Vigliensoni, G.; Fujinaga, I.
Document Analysis of Music Score Images with Selectional Auto-Encoders Proceedings Article
In: Proceedings of the19th International Society for Music Information Retrieval Conference, pp. 256-263, ISMIR 2018 Paris, France, 2018.
@inproceedings{k449,
title = {Document Analysis of Music Score Images with Selectional Auto-Encoders},
author = {F. J. Castellanos and J. Calvo-Zaragoza and G. Vigliensoni and I. Fujinaga},
year = {2018},
date = {2018-09-01},
booktitle = {Proceedings of the19th International Society for Music Information Retrieval Conference},
pages = {256-263},
address = {Paris, France},
organization = {ISMIR 2018},
keywords = {HispaMus},
pubstate = {published},
tppubtype = {inproceedings}
}
Calvo-Zaragoza, J.; Rizo, D.
End-to-End Neural Optical Music Recognition of Monophonic Scores Journal Article
In: Applied Sciences, vol. 8, no. 4, pp. 606–623, 2018, ISSN: 2076-3417.
@article{k390,
title = {End-to-End Neural Optical Music Recognition of Monophonic Scores},
author = {J. Calvo-Zaragoza and D. Rizo},
issn = {2076-3417},
year = {2018},
date = {2018-04-01},
journal = {Applied Sciences},
volume = {8},
number = {4},
pages = {606--623},
keywords = {HispaMus},
pubstate = {published},
tppubtype = {article}
}
Gallego, A. J.; Pertusa, A.; Calvo-Zaragoza, J.
Improving Convolutional Neural Networks’ Accuracy in Noisy Environments Using k-Nearest Neighbors Journal Article
In: Applied Sciences, vol. 8, no. 11, 2018, ISSN: 2076-3417.
Abstract | BibTeX | Tags: HispaMus
@article{k399,
title = {Improving Convolutional Neural Networks’ Accuracy in Noisy Environments Using k-Nearest Neighbors},
author = {A. J. Gallego and A. Pertusa and J. Calvo-Zaragoza},
issn = {2076-3417},
year = {2018},
date = {2018-01-01},
journal = {Applied Sciences},
volume = {8},
number = {11},
abstract = {We present a hybrid approach to improve the accuracy of Convolutional Neural Networks (CNN) without retraining the model. The proposed architecture replaces the softmax layer by a k-Nearest Neighbor (kNN) algorithm for inference. Although this is a common technique in transfer learning, we apply it to the same domain for which the network was trained. Previous works show that neural codes (neuron activations of the last hidden layers) can benefit from the inclusion of classifiers such as support vector machines or random forests. In this work, our proposed hybrid CNN + kNN architecture is evaluated using several image datasets, network topologies and label noise levels. The results show significant accuracy improvements in the inference stage with respect to the standard CNN with noisy labels, especially with relatively large datasets such as CIFAR100. We also verify that applying the ℓ and 2
norm on neural codes is statistically beneficial for this approach.},
keywords = {HispaMus},
pubstate = {published},
tppubtype = {article}
}
norm on neural codes is statistically beneficial for this approach.
Sober-Mira, J.; Calvo-Zaragoza, J.; Rizo, D.; Iñesta, J. M.
Pen-Based Music Document Transcription with Convolutional Neural Networks Book Chapter
In: Fornés, A.; Lamiroy, B. (Ed.): Graphics Recognition. Current Trends and Evolutions, Chapter 6, pp. 71–80, Springer, 2018, ISBN: 978-3-030-02284-6.
Abstract | BibTeX | Tags: HispaMus
@inbook{k400,
title = {Pen-Based Music Document Transcription with Convolutional Neural Networks},
author = {J. Sober-Mira and J. Calvo-Zaragoza and D. Rizo and J. M. Iñesta},
editor = {A. Fornés and B. Lamiroy},
isbn = {978-3-030-02284-6},
year = {2018},
date = {2018-01-01},
booktitle = {Graphics Recognition. Current Trends and Evolutions},
pages = {71--80},
publisher = {Springer},
chapter = {6},
abstract = {The transcription of music sources requires new ways of interacting with musical documents. Assuming that au- tomatic technologies will never guarantee a perfect transcription, our intention is to develop an interactive system in which user and software collaborate to complete the task. Since the use of traditional software for score edition might be tedious, our work studies the interaction by means of electronic pen (e-pen). In our framework, users trace symbols using an e-pen over a digital surface, which provides both the underlying image (offline data) and the drawing made (online data). Using both sources, the system is capable of reaching an error below 4% when recognizing the symbols with a Convolutional Neural Network.},
keywords = {HispaMus},
pubstate = {published},
tppubtype = {inbook}
}
Calvo-Zaragoza, J.; Castellanos, F. J.; Vigliensoni, G.; Fujinaga, I.
Deep Neural Networks for Document Processing of Music Score Images Journal Article
In: Applied Sciences, vol. 8, no. 5, pp. 654, 2018.
@article{k427,
title = {Deep Neural Networks for Document Processing of Music Score Images},
author = {J. Calvo-Zaragoza and F. J. Castellanos and G. Vigliensoni and I. Fujinaga},
year = {2018},
date = {2018-01-01},
urldate = {2018-01-01},
journal = {Applied Sciences},
volume = {8},
number = {5},
pages = {654},
keywords = {HispaMus},
pubstate = {published},
tppubtype = {article}
}