2018
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}
}
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}
}
Micó, L.; Iñesta, J. M.; Rizo, D.
Incremental Learning for Recognition of Handwritten Mensural Notation Proceedings Article
In: ICML joint workshop on Machine Learning for Music., 2018.
Abstract | Links | BibTeX | Tags: HispaMus
@inproceedings{k392,
title = {Incremental Learning for Recognition of Handwritten Mensural Notation},
author = {L. Micó and J. M. Iñesta and D. Rizo},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/392/incremental-learning-recognition.pdf},
year = {2018},
date = {2018-07-01},
urldate = {2018-07-01},
booktitle = {ICML joint workshop on Machine Learning for Music.},
abstract = {This paper presents an ongoing research on handwritten symbol recognition in early music scores. The help of human supervision is needed for a correct edition and publication of these collections. A suitable strategy is needed for optimizing the exploitation of human feedback to improve and adapt the classifier to the specificities of each manuscript. The objective is to minimize the number of interactions needed to solve the problem, thus optimizing the user workload. The strategy is shown to be convenient but there is still work ahead for improving its performance.},
keywords = {HispaMus},
pubstate = {published},
tppubtype = {inproceedings}
}
This paper presents an ongoing research on handwritten symbol recognition in early music scores. The help of human supervision is needed for a correct edition and publication of these collections. A suitable strategy is needed for optimizing the exploitation of human feedback to improve and adapt the classifier to the specificities of each manuscript. The objective is to minimize the number of interactions needed to solve the problem, thus optimizing the user workload. The strategy is shown to be convenient but there is still work ahead for improving its performance. Bustos, A.; Pertusa, A.
Learning Eligibility in Cancer Clinical Trials using Deep Neural Networks Journal Article
In: Applied Sciences, vol. 8, no. 7, 2018, ISSN: 2076-3417.
@article{k386,
title = {Learning Eligibility in Cancer Clinical Trials using Deep Neural Networks},
author = {A. Bustos and A. Pertusa},
issn = {2076-3417},
year = {2018},
date = {2018-07-01},
urldate = {2018-07-01},
journal = {Applied Sciences},
volume = {8},
number = {7},
abstract = {Interventional cancer clinical trials are generally too restrictive, and some patients are often excluded on the basis of comorbidity, past or concomitant treatments, or the fact that they are over a certain age. The efficacy and safety of new treatments for patients with these characteristics are, therefore, not defined. In this work, we built a model to automatically predict whether short clinical statements were considered inclusion or exclusion criteria. We used protocols from cancer clinical trials that were available in public registries from the last 18 years to train word-embeddings, and we constructed a dataset of 6M short free-texts labeled as eligible or not eligible. A text classifier was trained using deep neural networks, with pre-trained word-embeddings as inputs, to predict whether or not short free-text statements describing clinical information were considered eligible. We additionally analyzed the semantic reasoning of the word-embedding representations obtained and were able to identify equivalent treatments for a type of tumor analogous with the drugs used to treat other tumors. We show that representation learning using deep neural networks can be successfully leveraged to extract the medical knowledge from clinical trial protocols for potentially assisting practitioners when prescribing treatments.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Interventional cancer clinical trials are generally too restrictive, and some patients are often excluded on the basis of comorbidity, past or concomitant treatments, or the fact that they are over a certain age. The efficacy and safety of new treatments for patients with these characteristics are, therefore, not defined. In this work, we built a model to automatically predict whether short clinical statements were considered inclusion or exclusion criteria. We used protocols from cancer clinical trials that were available in public registries from the last 18 years to train word-embeddings, and we constructed a dataset of 6M short free-texts labeled as eligible or not eligible. A text classifier was trained using deep neural networks, with pre-trained word-embeddings as inputs, to predict whether or not short free-text statements describing clinical information were considered eligible. We additionally analyzed the semantic reasoning of the word-embedding representations obtained and were able to identify equivalent treatments for a type of tumor analogous with the drugs used to treat other tumors. We show that representation learning using deep neural networks can be successfully leveraged to extract the medical knowledge from clinical trial protocols for potentially assisting practitioners when prescribing treatments. 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.; Gil, P.; Pertusa, A.; Fisher, R. B.
Segmentation of Oil Spills on Side-Looking Airborne Radar Imagery with Autoencoders Journal Article
In: Sensors, vol. 18, no. 3, pp. 1424-8220, 2018, ISSN: 1424-8220.
@article{k385,
title = {Segmentation of Oil Spills on Side-Looking Airborne Radar Imagery with Autoencoders},
author = {A. J. Gallego and P. Gil and A. Pertusa and R. B. Fisher},
issn = {1424-8220},
year = {2018},
date = {2018-03-01},
journal = {Sensors},
volume = {18},
number = {3},
pages = {1424-8220},
abstract = {In this work, we use deep neural autoencoders to segment oil spills from Side-Looking Airborne Radar (SLAR) imagery. Synthetic Aperture Radar (SAR) has been much exploited for ocean surface monitoring, especially for oil pollution detection, but few approaches in the literature use SLAR. Our sensor consists of two SAR antennas mounted on an aircraft, enabling a quicker response than satellite sensors for emergency services when an oil spill occurs. Experiments on TERMA radar were carried out to detect oil spills on Spanish coasts using deep selectional autoencoders and RED-nets (very deep Residual Encoder-Decoder Networks). Different configurations of these networks were evaluated and the best topology significantly outperformed previous approaches, correctly detecting 100% of the spills and obtaining an F1 score of 93.01% at the pixel level. The proposed autoencoders perform accurately in SLAR imagery that has artifacts and noise caused by the aircraft maneuvers, in different weather conditions and with the presence of look-alikes due to natural phenomena such as shoals of fish and seaweed.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
In this work, we use deep neural autoencoders to segment oil spills from Side-Looking Airborne Radar (SLAR) imagery. Synthetic Aperture Radar (SAR) has been much exploited for ocean surface monitoring, especially for oil pollution detection, but few approaches in the literature use SLAR. Our sensor consists of two SAR antennas mounted on an aircraft, enabling a quicker response than satellite sensors for emergency services when an oil spill occurs. Experiments on TERMA radar were carried out to detect oil spills on Spanish coasts using deep selectional autoencoders and RED-nets (very deep Residual Encoder-Decoder Networks). Different configurations of these networks were evaluated and the best topology significantly outperformed previous approaches, correctly detecting 100% of the spills and obtaining an F1 score of 93.01% at the pixel level. The proposed autoencoders perform accurately in SLAR imagery that has artifacts and noise caused by the aircraft maneuvers, in different weather conditions and with the presence of look-alikes due to natural phenomena such as shoals of fish and seaweed. Castellanos, F. J.; Valero-Mas, J. J.; Calvo-Zaragoza, J.; Rico-Juan, J. R.
Oversampling imbalanced data in the string space Journal Article
In: Pattern Recognition Letters, vol. 103, pp. 32–38, 2018, ISSN: 0167-8655.
Abstract | BibTeX | Tags: GRE16-14
@article{k382,
title = {Oversampling imbalanced data in the string space},
author = {F. J. Castellanos and J. J. Valero-Mas and J. Calvo-Zaragoza and J. R. Rico-Juan},
issn = {0167-8655},
year = {2018},
date = {2018-02-01},
journal = {Pattern Recognition Letters},
volume = {103},
pages = {32--38},
abstract = {Imbalanced data is a typical problem in the supervised classification field, which occurs when the different classes are not equally represented. This fact typically results in the classifier biasing its performance towards the class representing the majority of the elements. Many methods have been proposed to alleviate this scenario, yet all of them assume that data is represented as feature vectors. In this paper we propose a strategy to balance a dataset whose samples are encoded as strings. Our approach is based on adapting the well-known Synthetic Minority Over-sampling Technique (SMOTE) algorithm to the string space. More precisely, data generation is achieved with an iterative approach to create artificial strings within the segment between two given samples of the training set. Results with several datasets and imbalance ratios show that the proposed strategy properly deals with the problem in all cases considered.},
keywords = {GRE16-14},
pubstate = {published},
tppubtype = {article}
}
Imbalanced data is a typical problem in the supervised classification field, which occurs when the different classes are not equally represented. This fact typically results in the classifier biasing its performance towards the class representing the majority of the elements. Many methods have been proposed to alleviate this scenario, yet all of them assume that data is represented as feature vectors. In this paper we propose a strategy to balance a dataset whose samples are encoded as strings. Our approach is based on adapting the well-known Synthetic Minority Over-sampling Technique (SMOTE) algorithm to the string space. More precisely, data generation is achieved with an iterative approach to create artificial strings within the segment between two given samples of the training set. Results with several datasets and imbalance ratios show that the proposed strategy properly deals with the problem in all cases considered. Gallego, A. J.; López, D.; Calera-Rubio, J.
Grammatical inference of directed acyclic graph languages with polynomial time complexity Journal Article
In: Journal of Computer and System Sciences, vol. 95, pp. 19-34, 2018, ISSN: 0022-0000.
@article{k514,
title = {Grammatical inference of directed acyclic graph languages with polynomial time complexity},
author = {A. J. Gallego and D. López and J. Calera-Rubio},
issn = {0022-0000},
year = {2018},
date = {2018-01-01},
journal = {Journal of Computer and System Sciences},
volume = {95},
pages = {19-34},
abstract = {In this paper we study the learning of graph languages. We extend the well-known classes of k-testability and k-testability in the strict sense languages to directed graph languages. We propose a grammatical inference algorithm to learn the class of directed acyclic k-testable in the strict sense graph languages. The algorithm runs in polynomial time and identifies this class of languages from positive data. We study its efficiency under several criteria, and perform a comprehensive experimentation with four datasets to show the validity of the method. Many fields, from pattern recognition to data compression, can take advantage of these results.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
In this paper we study the learning of graph languages. We extend the well-known classes of k-testability and k-testability in the strict sense languages to directed graph languages. We propose a grammatical inference algorithm to learn the class of directed acyclic k-testable in the strict sense graph languages. The algorithm runs in polynomial time and identifies this class of languages from positive data. We study its efficiency under several criteria, and perform a comprehensive experimentation with four datasets to show the validity of the method. Many fields, from pattern recognition to data compression, can take advantage of these results. 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}
}
Valero-Mas, J. J.; Benetos, E.; Iñesta, J. M.
A supervised classification approach for note tracking in polyphonic piano transcription Journal Article
In: Journal of New Music Research, vol. 47, no. 3, pp. 249–263, 2018, ISSN: 0929-8215.
Abstract | BibTeX | Tags: HispaMus
@article{k408,
title = {A supervised classification approach for note tracking in polyphonic piano transcription},
author = {J. J. Valero-Mas and E. Benetos and J. M. Iñesta},
issn = {0929-8215},
year = {2018},
date = {2018-01-01},
journal = {Journal of New Music Research},
volume = {47},
number = {3},
pages = {249--263},
abstract = {In the field of Automatic Music Transcription, note tracking systems constitute a key process in the overall success of the task as they compute the expected note-level abstraction out of a frame-based pitch activation representation. Despite its relevance, note tracking is most commonly performed using a set of hand-crafted rules adjusted in a manual fashion for the data at issue. In this regard, the present work introduces an approach based on machine learning, and more precisely supervised classification, that aims at automatically inferring such policies for the case of piano music. The idea is to segment each pitch band of a frame-based pitch activation into single instances which are subsequently classified as active or non-active note events. Results using a comprehensive set of supervised classification strategies on the MAPS piano data-set report its competitiveness against other commonly considered strategies for note tracking as well as an improvement of more than +10% in terms of F-measure when compared to the baseline considered for both frame-level and note-level evaluations.},
keywords = {HispaMus},
pubstate = {published},
tppubtype = {article}
}
In the field of Automatic Music Transcription, note tracking systems constitute a key process in the overall success of the task as they compute the expected note-level abstraction out of a frame-based pitch activation representation. Despite its relevance, note tracking is most commonly performed using a set of hand-crafted rules adjusted in a manual fashion for the data at issue. In this regard, the present work introduces an approach based on machine learning, and more precisely supervised classification, that aims at automatically inferring such policies for the case of piano music. The idea is to segment each pitch band of a frame-based pitch activation into single instances which are subsequently classified as active or non-active note events. Results using a comprehensive set of supervised classification strategies on the MAPS piano data-set report its competitiveness against other commonly considered strategies for note tracking as well as an improvement of more than +10% in terms of F-measure when compared to the baseline considered for both frame-level and note-level evaluations. Rizo, D.; Pascual-León, N.; Sapp, C. S.
White Mensural Manual Encoding: from Humdrum to MEI Journal Article
In: Cuadernos de Investigación Musical, no. 6, pp. 373-393, 2018, ISSN: Cuadernos de Investigación Music.
Links | BibTeX | Tags: HispaMus
@article{k403,
title = {White Mensural Manual Encoding: from Humdrum to MEI},
author = {D. Rizo and N. Pascual-León and C. S. Sapp},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/403/1953-8089-1-PB.pdf},
issn = {Cuadernos de Investigación Music},
year = {2018},
date = {2018-01-01},
journal = {Cuadernos de Investigación Musical},
number = {6},
pages = {373-393},
keywords = {HispaMus},
pubstate = {published},
tppubtype = {article}
}
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. 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. Gallego, A. J.; Pertusa, A.; Gil, P.
Automatic Ship Classification from Optical Aerial Images with Convolutional Neural Networks Journal Article
In: Remote Sensing, vol. 10, no. 4, pp. 20, 2018, ISSN: 2072-4292.
@article{k388,
title = {Automatic Ship Classification from Optical Aerial Images with Convolutional Neural Networks},
author = {A. J. Gallego and A. Pertusa and P. Gil},
issn = {2072-4292},
year = {2018},
date = {2018-01-01},
journal = {Remote Sensing},
volume = {10},
number = {4},
pages = {20},
abstract = {The automatic classification of ships from aerial images is a considerable challenge. Previous works have usually applied image processing and computer vision techniques to extract meaningful features from visible spectrum images in order to use them as the input for traditional supervised classifiers. We present a method for determining if an aerial image of visible spectrum contains a ship or not. The proposed architecture is based on Convolutional Neural Networks (CNN), and it combines neural codes extracted from a CNN with a k-Nearest Neighbor method so as to improve performance. The kNN results are compared to those obtained with the CNN Softmax output. Several CNN models have been configured and evaluated in order to seek the best hyperparameters, and the most suitable setting for this task was found by using transfer learning at different levels. A new dataset (named MASATI) composed of aerial imagery with more than 6000 samples has also been created to train and evaluate our architecture. The experimentation shows a success rate of over 99% for our approach, in contrast with the 79% obtained with traditional methods in classification of ship images, also outperforming other methods based on CNNs. A dataset of images (MWPU VHR-10) used in previous works was additionally used to evaluate the proposed approach. Our best setup achieves a success ratio of 86% with these data, significantly outperforming previous state-of-the-art ship classification methods.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
The automatic classification of ships from aerial images is a considerable challenge. Previous works have usually applied image processing and computer vision techniques to extract meaningful features from visible spectrum images in order to use them as the input for traditional supervised classifiers. We present a method for determining if an aerial image of visible spectrum contains a ship or not. The proposed architecture is based on Convolutional Neural Networks (CNN), and it combines neural codes extracted from a CNN with a k-Nearest Neighbor method so as to improve performance. The kNN results are compared to those obtained with the CNN Softmax output. Several CNN models have been configured and evaluated in order to seek the best hyperparameters, and the most suitable setting for this task was found by using transfer learning at different levels. A new dataset (named MASATI) composed of aerial imagery with more than 6000 samples has also been created to train and evaluate our architecture. The experimentation shows a success rate of over 99% for our approach, in contrast with the 79% obtained with traditional methods in classification of ship images, also outperforming other methods based on CNNs. A dataset of images (MWPU VHR-10) used in previous works was additionally used to evaluate the proposed approach. Our best setup achieves a success ratio of 86% with these data, significantly outperforming previous state-of-the-art ship classification methods. Iñesta, J. M.; Conklin, D.; Ramírez, R.; Fiore, T. M. M.
Machine Learning and Music Generation Book
Routledge, Taylor & Francis, 2018, ISBN: 978-0-8153-7720-7.
@book{k384,
title = {Machine Learning and Music Generation},
author = {J. M. Iñesta and D. Conklin and R. Ramírez and T. M. M. Fiore},
editor = {Thomas M. Fiore},
isbn = {978-0-8153-7720-7},
year = {2018},
date = {2018-01-01},
urldate = {2018-01-01},
pages = {111},
publisher = {Routledge, Taylor & Francis},
keywords = {TIMuL},
pubstate = {published},
tppubtype = {book}
}
Gallego, A. J.; Calvo-Zaragoza, J.; Valero-Mas, J. J.; Rico-Juan, J. R.
Clustering-based k-nearest neighbor classification for large-scale data with neural codes representation Journal Article
In: Pattern Recognition, vol. 74, pp. 531-543, 2018.
@article{k378,
title = {Clustering-based k-nearest neighbor classification for large-scale data with neural codes representation},
author = {A. J. Gallego and J. Calvo-Zaragoza and J. J. Valero-Mas and J. R. Rico-Juan},
year = {2018},
date = {2018-01-01},
urldate = {2018-01-01},
journal = {Pattern Recognition},
volume = {74},
pages = {531-543},
keywords = {TIMuL},
pubstate = {published},
tppubtype = {article}
}
Pertusa, A.; Gallego, A. J.; Bernabeu, M.
MirBot: A collaborative object recognition system for smartphones using convolutional neural networks Journal Article
In: Neurocomputing, vol. 293, pp. 87-99, 2018, ISSN: 0925-2312.
Abstract | BibTeX | Tags: TIMuL
@article{k366,
title = {MirBot: A collaborative object recognition system for smartphones using convolutional neural networks},
author = {A. Pertusa and A. J. Gallego and M. Bernabeu},
issn = {0925-2312},
year = {2018},
date = {2018-01-01},
urldate = {2018-01-01},
journal = {Neurocomputing},
volume = {293},
pages = {87-99},
abstract = {MirBot is a collaborative application for smartphones that allows users to perform object recognition. This app can be used to take a photograph of an object, select the region of interest and obtain the most likely class (dog, chair, etc.) by means of similarity search using features extracted from a convolutional neural network (CNN). The answers provided by the system can be validated by the user so as to improve the results for future queries. All the images are stored together with a series of metadata, thus enabling a multimodal incremental dataset labeled with synset identifiers from the WordNet ontology. This dataset grows continuously thanks to the users' feedback, and is publicly available for research. This work details the MirBot object recognition system, analyzes the statistics gathered after more than four years of usage, describes the image classification methodology, and performs an exhaustive evaluation using handcrafted features, neural codes, different transfer learning techniques, PCA compression and metadata, which can be used to improve the image classifier results. The app is freely available at the Apple and Google Play stores.},
keywords = {TIMuL},
pubstate = {published},
tppubtype = {article}
}
MirBot is a collaborative application for smartphones that allows users to perform object recognition. This app can be used to take a photograph of an object, select the region of interest and obtain the most likely class (dog, chair, etc.) by means of similarity search using features extracted from a convolutional neural network (CNN). The answers provided by the system can be validated by the user so as to improve the results for future queries. All the images are stored together with a series of metadata, thus enabling a multimodal incremental dataset labeled with synset identifiers from the WordNet ontology. This dataset grows continuously thanks to the users' feedback, and is publicly available for research. This work details the MirBot object recognition system, analyzes the statistics gathered after more than four years of usage, describes the image classification methodology, and performs an exhaustive evaluation using handcrafted features, neural codes, different transfer learning techniques, PCA compression and metadata, which can be used to improve the image classifier results. The app is freely available at the Apple and Google Play stores.2017
Sober-Mira, J.; Calvo-Zaragoza, J.; Rizo, D.; Iñesta, J. M.
Pen-based music document transcription Proceedings Article
In: Proceedings of GREC 2017, pp. 21–22, IEEE computer society, Kyoto (Japan), 2017, ISBN: 978-1-5386-3586-5.
@inproceedings{k381,
title = {Pen-based music document transcription},
author = {J. Sober-Mira and J. Calvo-Zaragoza and D. Rizo and J. M. Iñesta},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/381/3586c021.pdf},
isbn = {978-1-5386-3586-5},
year = {2017},
date = {2017-11-01},
booktitle = {Proceedings of GREC 2017},
pages = {21--22},
publisher = {IEEE computer society},
address = {Kyoto (Japan)},
keywords = {TIMuL},
pubstate = {published},
tppubtype = {inproceedings}
}
Calvo-Zaragoza, J.; Gallego, A. J.; Pertusa, A.
Recognition of Handwritten Music Symbols with Convolutional Neural Codes Proceedings Article
In: 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), pp. 691–696, Kyoto, Japan, 2017.
BibTeX | Tags: GRE16-14, TIMuL
@inproceedings{k376,
title = {Recognition of Handwritten Music Symbols with Convolutional Neural Codes},
author = {J. Calvo-Zaragoza and A. J. Gallego and A. Pertusa},
year = {2017},
date = {2017-11-01},
urldate = {2017-11-01},
booktitle = {14th IAPR International Conference on Document Analysis and Recognition (ICDAR)},
pages = {691--696},
address = {Kyoto, Japan},
keywords = {GRE16-14, TIMuL},
pubstate = {published},
tppubtype = {inproceedings}
}
Sober-Mira, J.; Calvo-Zaragoza, J.; Rizo, D.; Iñesta, J. M.
Multimodal Recognition for Music Document Transcription Proceedings Article
In: Proceedings of MML 2017, pp. 67–72, Barcelona, 2017.
@inproceedings{k380,
title = {Multimodal Recognition for Music Document Transcription},
author = {J. Sober-Mira and J. Calvo-Zaragoza and D. Rizo and J. M. Iñesta},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/380/mml17proceedings-67.pdf},
year = {2017},
date = {2017-10-01},
booktitle = {Proceedings of MML 2017},
pages = {67--72},
address = {Barcelona},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Hontanilla, M.; Pérez-Sancho, C.; Iñesta, J. M.
Music style recognition with language models -- beyond statistical results Proceedings Article
In: Proceedings of MML 2017, pp. 31–36, Barcelona, 2017.
@inproceedings{k379,
title = {Music style recognition with language models -- beyond statistical results},
author = {M. Hontanilla and C. Pérez-Sancho and J. M. Iñesta},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/379/mml17proceedings-35.pdf},
year = {2017},
date = {2017-10-01},
booktitle = {Proceedings of MML 2017},
pages = {31--36},
address = {Barcelona},
keywords = {TIMuL},
pubstate = {published},
tppubtype = {inproceedings}
}
Calvo-Zaragoza, J.; Valero-Mas, J. J.; Pertusa, A
End-To-End Optical Music Recognition using Neural Networks Proceedings Article
In: Proc. of International Society for Music Information Retrieval Conference (ISMIR), Suzhou, China, 2017.
Abstract | BibTeX | Tags: GRE16-14, TIMuL
@inproceedings{k374,
title = {End-To-End Optical Music Recognition using Neural Networks},
author = {J. Calvo-Zaragoza and J. J. Valero-Mas and A Pertusa},
year = {2017},
date = {2017-10-01},
booktitle = {Proc. of International Society for Music Information Retrieval Conference (ISMIR)},
address = {Suzhou, China},
abstract = {This work addresses the Optical Music Recognition (OMR) task in an end-to-end fashion using neural net- works. The proposed architecture is based on a Recurrent Convolutional Neural Network topology that takes as input an image of a monophonic score and retrieves a sequence of music symbols as output. In the first stage, a series of convolutional filters are trained to extract meaningful fea- tures of the input image, and then a recurrent block models the sequential nature of music. The system is trained us- ing a Connectionist Temporal Classification loss function, which avoids the need for a frame-by-frame alignment be- tween the image and the ground-truth music symbols. Ex- perimentation has been carried on a set of 90,000 synthetic monophonic music scores with more than 50 different pos- sible labels. Results obtained depict classification error rates around 2 % at symbol level, thus proving the po- tential of the proposed end-to-end architecture for OMR. The source code, dataset, and trained models are publicly released for reproducible research and future comparison purposes.},
keywords = {GRE16-14, TIMuL},
pubstate = {published},
tppubtype = {inproceedings}
}
This work addresses the Optical Music Recognition (OMR) task in an end-to-end fashion using neural net- works. The proposed architecture is based on a Recurrent Convolutional Neural Network topology that takes as input an image of a monophonic score and retrieves a sequence of music symbols as output. In the first stage, a series of convolutional filters are trained to extract meaningful fea- tures of the input image, and then a recurrent block models the sequential nature of music. The system is trained us- ing a Connectionist Temporal Classification loss function, which avoids the need for a frame-by-frame alignment be- tween the image and the ground-truth music symbols. Ex- perimentation has been carried on a set of 90,000 synthetic monophonic music scores with more than 50 different pos- sible labels. Results obtained depict classification error rates around 2 % at symbol level, thus proving the po- tential of the proposed end-to-end architecture for OMR. The source code, dataset, and trained models are publicly released for reproducible research and future comparison purposes. Alacid, B.; Gallego, A. J.; Gil, P.; Pertusa, A.
Oil Slicks Detection in SLAR Images with Autoencoders Proceedings Article
In: 5th International Symposium on Sensor Science, Barcelona, Spain, 2017.
@inproceedings{k375,
title = {Oil Slicks Detection in SLAR Images with Autoencoders},
author = {B. Alacid and A. J. Gallego and P. Gil and A. Pertusa},
year = {2017},
date = {2017-09-01},
urldate = {2017-09-01},
booktitle = {5th International Symposium on Sensor Science},
address = {Barcelona, Spain},
keywords = {ENJAMBRE},
pubstate = {published},
tppubtype = {inproceedings}
}
Bernabeu, J. F.
Similarity Learning and Stochastic Language Models for Tree-Represented Music PhD Thesis
2017.
@phdthesis{k377,
title = {Similarity Learning and Stochastic Language Models for Tree-Represented Music},
author = {J. F. Bernabeu},
editor = {José M. Iñesta and J. Calera-Rubio},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/377/BernabeuPhD.pdf},
year = {2017},
date = {2017-07-01},
organization = {University of Alicante},
keywords = {TIMuL},
pubstate = {published},
tppubtype = {phdthesis}
}
Valero-Mas, J. J.
Towards Interactive Multimodal Music Transcription PhD Thesis
2017.
@phdthesis{k371,
title = {Towards Interactive Multimodal Music Transcription},
author = {J. J. Valero-Mas},
editor = {José M. Iñesta},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/371/Thesis.pdf},
year = {2017},
date = {2017-07-01},
urldate = {2017-07-01},
organization = {University of Alicante},
keywords = {TIMuL},
pubstate = {published},
tppubtype = {phdthesis}
}
Valero-Mas, J. J.; Iñesta, J. M.
Experimental assessment of descriptive statistics and adaptive methodologies for threshold establishment in onset selection functions Proceedings Article
In: Proceedings of the 14th Sound and Music Computing Conference (SMC), pp. 117–124, Espoo (Finland), 2017.
@inproceedings{k368,
title = {Experimental assessment of descriptive statistics and adaptive methodologies for threshold establishment in onset selection functions},
author = {J. J. Valero-Mas and J. M. Iñesta},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/368/CameraReady.pdf},
year = {2017},
date = {2017-07-01},
booktitle = {Proceedings of the 14th Sound and Music Computing Conference (SMC)},
pages = {117--124},
address = {Espoo (Finland)},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Valero-Mas, J. J.; Benetos, E.; Iñesta, J. M.
Assessing the Relevance of Onset Information for Note Tracking in Piano Music Transcription Proceedings Article
In: Proceedings of the AES International Conference on Semantic Audio, Eerlangen, 2017.
@inproceedings{k363,
title = {Assessing the Relevance of Onset Information for Note Tracking in Piano Music Transcription},
author = {J. J. Valero-Mas and E. Benetos and J. M. Iñesta},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/363/CameraReady.pdf},
year = {2017},
date = {2017-06-21},
booktitle = {Proceedings of the AES International Conference on Semantic Audio},
address = {Eerlangen},
keywords = {TIMuL},
pubstate = {published},
tppubtype = {inproceedings}
}
Valero-Mas, J. J.; Calvo-Zaragoza, J.; Rico-Juan, J. R.; Iñesta, J. M.
A study of Prototype Selection algorithms for Nearest Neighbour in class-imbalanced problems Proceedings Article
In: Alexandre, J. S. Sánchez L. A.; Rodrigues, J. M. F. (Ed.): Proceedings of the 8th Iberian Conference on Pattern Recognition and Image Analysis (IbPRIA), pp. 335–343, Springer, Faro, Portugal, 2017, ISBN: 978-3-319-58837-7.
@inproceedings{k362,
title = {A study of Prototype Selection algorithms for Nearest Neighbour in class-imbalanced problems},
author = {J. J. Valero-Mas and J. Calvo-Zaragoza and J. R. Rico-Juan and J. M. Iñesta},
editor = {J. S. Sánchez L. A. Alexandre and J. M. F. Rodrigues},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/362/CameraReady.pdf},
isbn = {978-3-319-58837-7},
year = {2017},
date = {2017-06-01},
booktitle = {Proceedings of the 8th Iberian Conference on Pattern Recognition and Image Analysis (IbPRIA)},
pages = {335--343},
publisher = {Springer},
address = {Faro, Portugal},
keywords = {TIMuL},
pubstate = {published},
tppubtype = {inproceedings}
}
Rizo, D.; Calvo-Zaragoza, J.; Iñesta, J. M.; Fujinaga, I.
About agnostic representation of musical documents for Optical Music Recognition Proceedings Article
In: Music Encoding Conference, Tours, 2017, 2017.
@inproceedings{k369,
title = {About agnostic representation of musical documents for Optical Music Recognition},
author = {D. Rizo and J. Calvo-Zaragoza and J. M. Iñesta and I. Fujinaga},
year = {2017},
date = {2017-05-01},
booktitle = {Music Encoding Conference, Tours, 2017},
keywords = {TIMuL},
pubstate = {published},
tppubtype = {inproceedings}
}
Calvo-Zaragoza, J.; Oncina, J.
An efficient approach for Interactive Sequential Pattern Recognition Journal Article
In: Pattern Recognition, vol. 64, pp. 295-304, 2017.
@article{k359,
title = {An efficient approach for Interactive Sequential Pattern Recognition},
author = {J. Calvo-Zaragoza and J. Oncina},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/359/efficient-approach-sequential.pdf},
year = {2017},
date = {2017-04-01},
journal = {Pattern Recognition},
volume = {64},
pages = {295-304},
keywords = {TIMuL},
pubstate = {published},
tppubtype = {article}
}
Calvo-Zaragoza, J.; Oncina, J.
Recognition of Pen-based Music Notation with Finite-State Machines Journal Article
In: Expert Systems With Applications, vol. 72, pp. 395-406, 2017.
@article{k358,
title = {Recognition of Pen-based Music Notation with Finite-State Machines},
author = {J. Calvo-Zaragoza and J. Oncina},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/358/recognition-pen-based.pdf},
year = {2017},
date = {2017-04-01},
journal = {Expert Systems With Applications},
volume = {72},
pages = {395-406},
keywords = {TIMuL},
pubstate = {published},
tppubtype = {article}
}
Rizo, D.; Pascual, B.; Iñesta, J. M.; González, L. A.; Ezquerro, A.
Towards the Digital Encoding of Hispanic White Mensural Notation Journal Article
In: Anuario Musical, no. 72, pp. 293–304, 2017, ISSN: 0211-3538.
Abstract | BibTeX | Tags: TIMuL
@article{k383,
title = {Towards the Digital Encoding of Hispanic White Mensural Notation},
author = {D. Rizo and B. Pascual and J. M. Iñesta and L. A. González and A. Ezquerro},
issn = {0211-3538},
year = {2017},
date = {2017-01-01},
urldate = {2017-01-01},
journal = {Anuario Musical},
number = {72},
pages = {293--304},
abstract = {In this work, the elements necessary for digitally encoding music contained in manuscripts from the centuries 16th to 17th are introduced. The solutions proposed to overcome the difficulties that generate some of the aspects that make this notation different from the modern Western notation are presented. Problems faced are, for example, the absence of bar lines or the duration of notes that are based on the context. The new typographic font 'Capitán', created specifically to represent this type of early notation, is also presented.},
keywords = {TIMuL},
pubstate = {published},
tppubtype = {article}
}
In this work, the elements necessary for digitally encoding music contained in manuscripts from the centuries 16th to 17th are introduced. The solutions proposed to overcome the difficulties that generate some of the aspects that make this notation different from the modern Western notation are presented. Problems faced are, for example, the absence of bar lines or the duration of notes that are based on the context. The new typographic font 'Capitán', created specifically to represent this type of early notation, is also presented. Gallego, A. J.; Calvo-Zaragoza, J.
Staff-line removal with Selectional Auto-Encoders Journal Article
In: Expert Systems With Applications, vol. 89, pp. 138 - 148, 2017, ISSN: 0957-4174.
Abstract | Links | BibTeX | Tags: TIMuL
@article{k372,
title = {Staff-line removal with Selectional Auto-Encoders},
author = {A. J. Gallego and J. Calvo-Zaragoza},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/372/staff-line-removal.pdf},
issn = {0957-4174},
year = {2017},
date = {2017-01-01},
urldate = {2017-01-01},
journal = {Expert Systems With Applications},
volume = {89},
pages = {138 - 148},
abstract = {Staff-line removal is an important preprocessing stage as regards most Optical Music Recognition systems. The common procedures employed to carry out this task involve image processing techniques. In contrast to these traditional methods, which are based on hand-engineered transformations, the problem can also be approached from a machine learning point of view if representative examples of the task are provided. We propose doing this through the use of a new approach involving auto-encoders, which select the appropriate features of an input feature set (Selectional Auto-Encoders). Within the context of the problem at hand, the model is trained to select those pixels of a given image that belong to a musical symbol, thus removing the lines of the staves. Our results show that the proposed technique is quite competitive and significantly outperforms the other state-of-art strategies considered, particularly when dealing with grayscale input images.},
keywords = {TIMuL},
pubstate = {published},
tppubtype = {article}
}
Staff-line removal is an important preprocessing stage as regards most Optical Music Recognition systems. The common procedures employed to carry out this task involve image processing techniques. In contrast to these traditional methods, which are based on hand-engineered transformations, the problem can also be approached from a machine learning point of view if representative examples of the task are provided. We propose doing this through the use of a new approach involving auto-encoders, which select the appropriate features of an input feature set (Selectional Auto-Encoders). Within the context of the problem at hand, the model is trained to select those pixels of a given image that belong to a musical symbol, thus removing the lines of the staves. Our results show that the proposed technique is quite competitive and significantly outperforms the other state-of-art strategies considered, particularly when dealing with grayscale input images. Valero-Mas, J. J.; Iñesta, J. M.
Interactive User Correction of Automatically Detected Onsets: Approach and Evaluation Journal Article
In: EURASIP Journal on Audio, Speech, and Music Processing, no. 15, 2017, ISSN: 1687-4722.
@article{k367,
title = {Interactive User Correction of Automatically Detected Onsets: Approach and Evaluation},
author = {J. J. Valero-Mas and J. M. Iñesta},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/367/EURASIP_Valero-MasInesta-2017.pdf},
issn = {1687-4722},
year = {2017},
date = {2017-01-01},
journal = {EURASIP Journal on Audio, Speech, and Music Processing},
number = {15},
keywords = {TIMuL},
pubstate = {published},
tppubtype = {article}
}
Calvo-Zaragoza, J.; Pertusa, A.; Oncina, J.
Staff-line detection and removal using a convolutional neural network Journal Article
In: Machine Vision and Applications, pp. 1-10, 2017, ISSN: 1432-1769.
Abstract | BibTeX | Tags: TIMuL
@article{k365,
title = {Staff-line detection and removal using a convolutional neural network},
author = {J. Calvo-Zaragoza and A. Pertusa and J. Oncina},
issn = {1432-1769},
year = {2017},
date = {2017-01-01},
urldate = {2017-01-01},
journal = {Machine Vision and Applications},
pages = {1-10},
abstract = {Staff-line removal is an important preprocessing stage for most optical music recognition systems. Common procedures to solve this task involve image processing techniques. In contrast to these traditional methods based on hand-engineered transformations, the problem can also be approached as a classification task in which each pixel is labeled as either staff or symbol, so that only those that belong to symbols are kept in the image. In order to perform this classification, we propose the use of convolutional neural networks, which have demonstrated an outstanding performance in image retrieval tasks. The initial features of each pixel consist of a square patch from the input image centered at that pixel. The proposed network is trained by using a dataset which contains pairs of scores with and without the staff lines. Our results in both binary and grayscale images show that the proposed technique is very accurate, outperforming both other classifiers and the state-of-the-art strategies considered. In addition, several advantages of the presented methodology with respect to traditional procedures proposed so far are discussed.},
keywords = {TIMuL},
pubstate = {published},
tppubtype = {article}
}
Staff-line removal is an important preprocessing stage for most optical music recognition systems. Common procedures to solve this task involve image processing techniques. In contrast to these traditional methods based on hand-engineered transformations, the problem can also be approached as a classification task in which each pixel is labeled as either staff or symbol, so that only those that belong to symbols are kept in the image. In order to perform this classification, we propose the use of convolutional neural networks, which have demonstrated an outstanding performance in image retrieval tasks. The initial features of each pixel consist of a square patch from the input image centered at that pixel. The proposed network is trained by using a dataset which contains pairs of scores with and without the staff lines. Our results in both binary and grayscale images show that the proposed technique is very accurate, outperforming both other classifiers and the state-of-the-art strategies considered. In addition, several advantages of the presented methodology with respect to traditional procedures proposed so far are discussed. Calvo-Zaragoza, J.; Vigliensoni, G.; Fujinaga, I.
Pixel-wise Binarization of Musical Documents with Convolutional Neural Networks Proceedings Article
In: Proceedings of the 15th IAPR International Conference on Machine Vision Applications, 2017.
@inproceedings{k361,
title = {Pixel-wise Binarization of Musical Documents with Convolutional Neural Networks},
author = {J. Calvo-Zaragoza and G. Vigliensoni and I. Fujinaga},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/361/pixel-wise-binarization.pdf},
year = {2017},
date = {2017-01-01},
booktitle = {Proceedings of the 15th IAPR International Conference on Machine Vision Applications},
keywords = {TIMuL},
pubstate = {published},
tppubtype = {inproceedings}
}
Calvo-Zaragoza, J.; Vigliensoni, G.; Fujinaga, I.
A machine learning framework for the categorization of elements in images of musical documents Proceedings Article
In: Proceedings of the Third International Conference on Technologies for Music Notation and Representation, 2017.
@inproceedings{k360,
title = {A machine learning framework for the categorization of elements in images of musical documents},
author = {J. Calvo-Zaragoza and G. Vigliensoni and I. Fujinaga},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/360/tenor-unified-categorization.pdf},
year = {2017},
date = {2017-01-01},
booktitle = {Proceedings of the Third International Conference on Technologies for Music Notation and Representation},
keywords = {TIMuL},
pubstate = {published},
tppubtype = {inproceedings}
}
Valero-Mas, J. J.; Calvo-Zaragoza, J.; Rico-Juan, J. R.; Iñesta, J. M.
An Experimental Study on Rank Methods for Prototype Selection Journal Article
In: Soft Computing, vol. 21, no. 19, pp. 5703-–5715, 2017, ISSN: 1432-7643.
Abstract | Links | BibTeX | Tags: TIMuL
@article{k339,
title = {An Experimental Study on Rank Methods for Prototype Selection},
author = {J. J. Valero-Mas and J. Calvo-Zaragoza and J. R. Rico-Juan and J. M. Iñesta},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/339/SOCO-RankMethods-2016.pdf},
issn = {1432-7643},
year = {2017},
date = {2017-01-01},
journal = {Soft Computing},
volume = {21},
number = {19},
pages = {5703-–5715},
abstract = {Prototype selection is one of the most popular approaches for addressing the low efficiency issue typically found in the well-known k-Nearest Neighbour classification rule. These techniques select a representative subset from an original collection of prototypes with the premise of main- taining the same classification accuracy. Most recently, rank methods have been proposed as an alternative to develop new selection strategies. Following a certain heuristic, these methods sort the elements of the initial collection accord- ing to their relevance and then select the best possible subset by means of a parameter representing the amount of data to maintain. Due to the relative novelty of these methods, their performance and competitiveness against other strategies is still unclear. This work performs an exhaustive experimental study of such methods for prototype selection. A represen- tative collection of both classic and sophisticated algorithms are compared to the aforementioned techniques in a num- ber of datasets, including different levels of induced noise. Results report the remarkable competitiveness of these rank methods as well as their excellent trade-off between proto- type reduction and achieved accuracy.},
keywords = {TIMuL},
pubstate = {published},
tppubtype = {article}
}
Prototype selection is one of the most popular approaches for addressing the low efficiency issue typically found in the well-known k-Nearest Neighbour classification rule. These techniques select a representative subset from an original collection of prototypes with the premise of main- taining the same classification accuracy. Most recently, rank methods have been proposed as an alternative to develop new selection strategies. Following a certain heuristic, these methods sort the elements of the initial collection accord- ing to their relevance and then select the best possible subset by means of a parameter representing the amount of data to maintain. Due to the relative novelty of these methods, their performance and competitiveness against other strategies is still unclear. This work performs an exhaustive experimental study of such methods for prototype selection. A represen- tative collection of both classic and sophisticated algorithms are compared to the aforementioned techniques in a num- ber of datasets, including different levels of induced noise. Results report the remarkable competitiveness of these rank methods as well as their excellent trade-off between proto- type reduction and achieved accuracy.2016
Bellet, A.; Bernabeu, J. F.; Habrard, A.; Sebban, M.
Learning discriminative tree edit similarities for linear classification - Application to melody recognition Journal Article
In: Neurocomputing, vol. 214, pp. 155-161, 2016.
Abstract | Links | BibTeX | Tags: TIMuL
@article{k349,
title = {Learning discriminative tree edit similarities for linear classification - Application to melody recognition},
author = {A. Bellet and J. F. Bernabeu and A. Habrard and M. Sebban},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/349/ldTree2016.pdf},
year = {2016},
date = {2016-11-01},
urldate = {2016-11-01},
journal = {Neurocomputing},
volume = {214},
pages = {155-161},
abstract = {Similarity functions are a fundamental component of many learning algorithms. When dealing with string or tree-structured data, measures based on the edit distance are widely used, and there exist a few methods for learning them from data. In this context, we recently proposed GESL (Bellet et al., 2012 [3]), an approach to string edit similarity learning based on loss minimization which offers theoretical guarantees as to the generalization ability and discriminative power of the learned similarities. In this paper, we argue that GESL, which has been originally dedicated to deal with strings, can be extended to trees and lead to powerful and competitive similarities. We illustrate this claim on a music recognition task, namely melody classification, where each piece is represented as a tree modeling its structure as well as rhythm and pitch information. The results show that GESL outperforms standard as well as probabilistically-learned edit distances and that it is able to describe consistently the underlying melodic similarity model.},
keywords = {TIMuL},
pubstate = {published},
tppubtype = {article}
}
Similarity functions are a fundamental component of many learning algorithms. When dealing with string or tree-structured data, measures based on the edit distance are widely used, and there exist a few methods for learning them from data. In this context, we recently proposed GESL (Bellet et al., 2012 [3]), an approach to string edit similarity learning based on loss minimization which offers theoretical guarantees as to the generalization ability and discriminative power of the learned similarities. In this paper, we argue that GESL, which has been originally dedicated to deal with strings, can be extended to trees and lead to powerful and competitive similarities. We illustrate this claim on a music recognition task, namely melody classification, where each piece is represented as a tree modeling its structure as well as rhythm and pitch information. The results show that GESL outperforms standard as well as probabilistically-learned edit distances and that it is able to describe consistently the underlying melodic similarity model. Iñesta, J. M.; Conklin, D.; Ramírez, R.
Machine learning and music generation Journal Article
In: Journal of Mathematics and Music, vol. 10, no. 2, pp. 87–91, 2016, ISSN: 1745-9737.
Abstract | Links | BibTeX | Tags:
@article{k357,
title = {Machine learning and music generation},
author = {J. M. Iñesta and D. Conklin and R. Ramírez},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/357/jmm2016-editorial.pdf},
issn = {1745-9737},
year = {2016},
date = {2016-10-01},
journal = {Journal of Mathematics and Music},
volume = {10},
number = {2},
pages = {87--91},
abstract = {Computational approaches to music composition and style imitation have engaged musicians, music scholars, and computer scientists since the early days of computing. Music generation research has generally employed one of two strategies: knowledge-based methods that model style through explicitly formalized rules, and data mining methods that apply machine learning to induce statistical models of musical style.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Computational approaches to music composition and style imitation have engaged musicians, music scholars, and computer scientists since the early days of computing. Music generation research has generally employed one of two strategies: knowledge-based methods that model style through explicitly formalized rules, and data mining methods that apply machine learning to induce statistical models of musical style. Rizo, D.; Calvo-Zaragoza, J.; Iñesta, J. M.; Illescas, P. R.
Hidden Markov Models for Functional Analysis Proceedings Article
In: Music and Machine Learning Workshop, Riva del Garda, 2016.
@inproceedings{k370,
title = {Hidden Markov Models for Functional Analysis},
author = {D. Rizo and J. Calvo-Zaragoza and J. M. Iñesta and P. R. Illescas},
year = {2016},
date = {2016-09-01},
booktitle = {Music and Machine Learning Workshop, Riva del Garda},
keywords = {TIMuL},
pubstate = {published},
tppubtype = {inproceedings}
}
Valero-Mas, J. J.; Benetos, E.; Iñesta, J. M.
Classification-based Note Tracking for Automatic Music Transcription Proceedings Article
In: Proceedings of the 9th Machine Learning and Music Workshop (MML2016), pp. 61–65, European Conference on Machine Learning and Principles and Practice of Knowledge Discovery (ECML-PKDD) Riva del Garda, Italy, 2016.
@inproceedings{k352,
title = {Classification-based Note Tracking for Automatic Music Transcription},
author = {J. J. Valero-Mas and E. Benetos and J. M. Iñesta},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/352/ValeroMasBenetosInesta-MML2016.pdf},
year = {2016},
date = {2016-09-01},
booktitle = {Proceedings of the 9th Machine Learning and Music Workshop (MML2016)},
pages = {61--65},
address = {Riva del Garda, Italy},
organization = {European Conference on Machine Learning and Principles and Practice of Knowledge Discovery (ECML-PKDD)},
keywords = {TIMuL},
pubstate = {published},
tppubtype = {inproceedings}
}
Rizo, D.; Marsden, A.
A standard format proposal for hierarchical analyses and representations Proceedings Article
In: Proceedings of the 3rd International Workshop on Digital Libraries for Musicology, pp. 25–32, ACM, New York, USA, 2016, ISBN: 978-1-4503-4751-8.
Abstract | BibTeX | Tags: TIMuL
@inproceedings{k356,
title = {A standard format proposal for hierarchical analyses and representations},
author = {D. Rizo and A. Marsden},
isbn = {978-1-4503-4751-8},
year = {2016},
date = {2016-08-01},
booktitle = {Proceedings of the 3rd International Workshop on Digital Libraries for Musicology},
pages = {25--32},
publisher = {ACM},
address = {New York, USA},
abstract = {In the realm of digital musicology, standardizations efforts to date have mostly concentrated on the representation of music. Anal- yses of music are increasingly being generated or communicated by digital means. We demonstrate that the same arguments for the desirability of standardization in the representation of music apply also to the representation of analyses of music: proper preservation, sharing of data, and facilitation of digital processing. We concen- trate here on analyses which can be described as hierarchical and show that this covers a broad range of existing analytical formats. We propose an extension of MEI (Music Encoding Initiative) to al- low the encoding of analyses unambiguously associated with and aligned to a representation of the music analysed, making use of existing mechanisms within MEI’ and s parent TEI (Text Encoding Ini- tiative) for the representation of trees and graphs.},
keywords = {TIMuL},
pubstate = {published},
tppubtype = {inproceedings}
}
In the realm of digital musicology, standardizations efforts to date have mostly concentrated on the representation of music. Anal- yses of music are increasingly being generated or communicated by digital means. We demonstrate that the same arguments for the desirability of standardization in the representation of music apply also to the representation of analyses of music: proper preservation, sharing of data, and facilitation of digital processing. We concen- trate here on analyses which can be described as hierarchical and show that this covers a broad range of existing analytical formats. We propose an extension of MEI (Music Encoding Initiative) to al- low the encoding of analyses unambiguously associated with and aligned to a representation of the music analysed, making use of existing mechanisms within MEI’ and s parent TEI (Text Encoding Ini- tiative) for the representation of trees and graphs. Calvo-Zaragoza, J.; Rizo, D.; Iñesta, J. M.
Two (note) heads are better than one: pen-based multimodal interaction with music scores Proceedings Article
In: Devaney, J. (Ed.): 17th International Society for Music Information Retrieval Conference, pp. 509-514, New York City, 2016, ISBN: 978-0-692-75506-8.
@inproceedings{k345,
title = {Two (note) heads are better than one: pen-based multimodal interaction with music scores},
author = {J. Calvo-Zaragoza and D. Rizo and J. M. Iñesta},
editor = {J. Devaney},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/345/two-note-heads.pdf},
isbn = {978-0-692-75506-8},
year = {2016},
date = {2016-08-01},
booktitle = {17th International Society for Music Information Retrieval Conference},
pages = {509-514},
address = {New York City},
keywords = {TIMuL},
pubstate = {published},
tppubtype = {inproceedings}
}
Valero-Mas, J. J.; Calvo-Zaragoza, J.; Rico-Juan, J. R.
On the suitability of Prototype Selection methods for kNN classification with distributed data Journal Article
In: Neurocomputing, vol. 203, pp. 150-160, 2016.
@article{k341,
title = {On the suitability of Prototype Selection methods for kNN classification with distributed data},
author = {J. J. Valero-Mas and J. Calvo-Zaragoza and J. R. Rico-Juan},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/341/SuitabilityPSDistributedScenarios.pdf},
year = {2016},
date = {2016-08-01},
journal = {Neurocomputing},
volume = {203},
pages = {150-160},
keywords = {TIMuL},
pubstate = {published},
tppubtype = {article}
}
Iñesta, J. M.; de León, P. J. Ponce
Data-based melody generation through multi-objective evolutionary computation Journal Article
In: Journal of Mathematics and Music, vol. 10, no. 2, pp. 173-192, 2016, ISSN: 1745-9737.
Abstract | Links | BibTeX | Tags: TIMuL
@article{k344,
title = {Data-based melody generation through multi-objective evolutionary computation},
author = {J. M. Iñesta and P. J. Ponce de León},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/344/Data+based+melody+generation+through+multi+objective+evolutionary+computation+%28post-print%29.pdf},
issn = {1745-9737},
year = {2016},
date = {2016-07-01},
urldate = {2016-07-01},
journal = {Journal of Mathematics and Music},
volume = {10},
number = {2},
pages = {173-192},
abstract = {Genetic-based composition algorithms are able to explore an immense space of possibilities, but the main difficulty has always been the implementation of the selection process. In this work, sets of melodies are utilized for training a machine learning approach to compute fitness, based on different metrics. The fitness of a candidate is provided by combining the metrics, but their values can range through different orders of magnitude and evolve in different ways, which makes it hard to combine these criteria. In order to solve this problem, a multi-objective fitness approach is proposed, in which the best individuals are those in the Pareto front of the multi-dimensional fitness space. Melodic trees are also proposed as a data structure for chromosomic representation of melodies and genetic operators are adapted to them. Some experiments have been carried out using a graphical interface prototype that allows one to explore the creative capabilities of the proposed system. An Online Supplement is provided and can be accessed at http://dx.doi.org/10.1080/17459737.2016.1188171, where the reader can find some technical details, information about the data used, generated melodies, and additional information about the developed prototype and its performance.},
keywords = {TIMuL},
pubstate = {published},
tppubtype = {article}
}
Genetic-based composition algorithms are able to explore an immense space of possibilities, but the main difficulty has always been the implementation of the selection process. In this work, sets of melodies are utilized for training a machine learning approach to compute fitness, based on different metrics. The fitness of a candidate is provided by combining the metrics, but their values can range through different orders of magnitude and evolve in different ways, which makes it hard to combine these criteria. In order to solve this problem, a multi-objective fitness approach is proposed, in which the best individuals are those in the Pareto front of the multi-dimensional fitness space. Melodic trees are also proposed as a data structure for chromosomic representation of melodies and genetic operators are adapted to them. Some experiments have been carried out using a graphical interface prototype that allows one to explore the creative capabilities of the proposed system. An Online Supplement is provided and can be accessed at http://dx.doi.org/10.1080/17459737.2016.1188171, where the reader can find some technical details, information about the data used, generated melodies, and additional information about the developed prototype and its performance. Calvo-Zaragoza, J.; Oncina, J.; Higuera, C. De La
Computing the Expected Edit Distance from a String to a PFA Proceedings Article
In: Han, Yo-Sub; Salomaa, Kai (Ed.): 21st International Conference Implementation and Application of Automata, pp. 39-50, Springer, 2016.
@inproceedings{k342,
title = {Computing the Expected Edit Distance from a String to a PFA},
author = {J. Calvo-Zaragoza and J. Oncina and C. De La Higuera},
editor = {Yo-Sub Han and Kai Salomaa},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/342/distance-string-pfa.pdf},
year = {2016},
date = {2016-07-01},
urldate = {2016-07-01},
booktitle = {21st International Conference Implementation and Application of Automata},
pages = {39-50},
publisher = {Springer},
keywords = {TIMuL},
pubstate = {published},
tppubtype = {inproceedings}
}
Bernabeu, M.; Pertusa, A.; Gallego, A. J.
Image spatial verification using Segment Intersection of Interest Points Proceedings Article
In: Proc. of the 24 Int. Conf. in Central Europe on Computer Graphics, Visualization and Computer Vision (WSCG), 2016, ISBN: 2464-4614.
@inproceedings{k346,
title = {Image spatial verification using Segment Intersection of Interest Points},
author = {M. Bernabeu and A. Pertusa and A. J. Gallego},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/346/imageSpatialVerification.pdf},
isbn = {2464-4614},
year = {2016},
date = {2016-05-01},
booktitle = {Proc. of the 24 Int. Conf. in Central Europe on Computer Graphics, Visualization and Computer Vision (WSCG)},
keywords = {TIMuL},
pubstate = {published},
tppubtype = {inproceedings}
}
Rizo, D.; Illescas, P. R.; Iñesta, J. M.
Interactive melodic analysis Book Chapter
In: Meredith, D. (Ed.): Computational Music Analysis, Chapter 7, pp. 191-219, Springer, 2016, ISBN: 978-3-319-25931-4.
Abstract | Links | BibTeX | Tags: GRE-12-34, Prometeo 2012, TIMuL
@inbook{k322,
title = {Interactive melodic analysis},
author = {D. Rizo and P. R. Illescas and J. M. Iñesta},
editor = {D. Meredith},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/322/RizoEtAl.pdf},
isbn = {978-3-319-25931-4},
year = {2016},
date = {2016-01-01},
urldate = {2016-01-01},
booktitle = {Computational Music Analysis},
pages = {191-219},
publisher = {Springer},
chapter = {7},
abstract = {Melodic analysis sets the importance and role of each note in a particular harmonic context. Thus, a note is classified as a harmonic tone, when it belongs to the underlying chord, and as a non harmonic tone otherwise, with a number of categories in this latter case. Automatic systems for solving this task are still far from being available, so it must be assumed that in a practical scenario the human expert must correct the system’s output. Interactive systems allow for turning the user into a source of high-quality and high-confidence training data, so on-line ma- chine learning and interactive pattern recognition provide tools that have proven to be very convenient in this context.},
keywords = {GRE-12-34, Prometeo 2012, TIMuL},
pubstate = {published},
tppubtype = {inbook}
}
Melodic analysis sets the importance and role of each note in a particular harmonic context. Thus, a note is classified as a harmonic tone, when it belongs to the underlying chord, and as a non harmonic tone otherwise, with a number of categories in this latter case. Automatic systems for solving this task are still far from being available, so it must be assumed that in a practical scenario the human expert must correct the system’s output. Interactive systems allow for turning the user into a source of high-quality and high-confidence training data, so on-line ma- chine learning and interactive pattern recognition provide tools that have proven to be very convenient in this context. Rizo, D.; Pascual, B.; Ezquerro, A.; Iñesta, J. M.; González, L. A.
Tipografía y transductor para la transcripción musical interactiva de notación mensural hispánica Proceedings Article
In: Libro de actas de las I jornadas sobre la investigación en los centros superiores de enseñanzas artísticas, pp. 6–23, ISEACV, Valencia, 2016, ISBN: 978-84-608-6758-6.
@inproceedings{k364,
title = {Tipografía y transductor para la transcripción musical interactiva de notación mensural hispánica},
author = {D. Rizo and B. Pascual and A. Ezquerro and J. M. Iñesta and L. A. González},
isbn = {978-84-608-6758-6},
year = {2016},
date = {2016-01-01},
urldate = {2016-01-01},
booktitle = {Libro de actas de las I jornadas sobre la investigación en los centros superiores de enseñanzas artísticas},
pages = {6--23},
publisher = {ISEACV},
address = {Valencia},
keywords = {TIMuL},
pubstate = {published},
tppubtype = {inproceedings}
}
2018
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}
}
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}
}
Micó, L.; Iñesta, J. M.; Rizo, D.
Incremental Learning for Recognition of Handwritten Mensural Notation Proceedings Article
In: ICML joint workshop on Machine Learning for Music., 2018.
Abstract | Links | BibTeX | Tags: HispaMus
@inproceedings{k392,
title = {Incremental Learning for Recognition of Handwritten Mensural Notation},
author = {L. Micó and J. M. Iñesta and D. Rizo},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/392/incremental-learning-recognition.pdf},
year = {2018},
date = {2018-07-01},
urldate = {2018-07-01},
booktitle = {ICML joint workshop on Machine Learning for Music.},
abstract = {This paper presents an ongoing research on handwritten symbol recognition in early music scores. The help of human supervision is needed for a correct edition and publication of these collections. A suitable strategy is needed for optimizing the exploitation of human feedback to improve and adapt the classifier to the specificities of each manuscript. The objective is to minimize the number of interactions needed to solve the problem, thus optimizing the user workload. The strategy is shown to be convenient but there is still work ahead for improving its performance.},
keywords = {HispaMus},
pubstate = {published},
tppubtype = {inproceedings}
}
This paper presents an ongoing research on handwritten symbol recognition in early music scores. The help of human supervision is needed for a correct edition and publication of these collections. A suitable strategy is needed for optimizing the exploitation of human feedback to improve and adapt the classifier to the specificities of each manuscript. The objective is to minimize the number of interactions needed to solve the problem, thus optimizing the user workload. The strategy is shown to be convenient but there is still work ahead for improving its performance.
Bustos, A.; Pertusa, A.
Learning Eligibility in Cancer Clinical Trials using Deep Neural Networks Journal Article
In: Applied Sciences, vol. 8, no. 7, 2018, ISSN: 2076-3417.
@article{k386,
title = {Learning Eligibility in Cancer Clinical Trials using Deep Neural Networks},
author = {A. Bustos and A. Pertusa},
issn = {2076-3417},
year = {2018},
date = {2018-07-01},
urldate = {2018-07-01},
journal = {Applied Sciences},
volume = {8},
number = {7},
abstract = {Interventional cancer clinical trials are generally too restrictive, and some patients are often excluded on the basis of comorbidity, past or concomitant treatments, or the fact that they are over a certain age. The efficacy and safety of new treatments for patients with these characteristics are, therefore, not defined. In this work, we built a model to automatically predict whether short clinical statements were considered inclusion or exclusion criteria. We used protocols from cancer clinical trials that were available in public registries from the last 18 years to train word-embeddings, and we constructed a dataset of 6M short free-texts labeled as eligible or not eligible. A text classifier was trained using deep neural networks, with pre-trained word-embeddings as inputs, to predict whether or not short free-text statements describing clinical information were considered eligible. We additionally analyzed the semantic reasoning of the word-embedding representations obtained and were able to identify equivalent treatments for a type of tumor analogous with the drugs used to treat other tumors. We show that representation learning using deep neural networks can be successfully leveraged to extract the medical knowledge from clinical trial protocols for potentially assisting practitioners when prescribing treatments.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Interventional cancer clinical trials are generally too restrictive, and some patients are often excluded on the basis of comorbidity, past or concomitant treatments, or the fact that they are over a certain age. The efficacy and safety of new treatments for patients with these characteristics are, therefore, not defined. In this work, we built a model to automatically predict whether short clinical statements were considered inclusion or exclusion criteria. We used protocols from cancer clinical trials that were available in public registries from the last 18 years to train word-embeddings, and we constructed a dataset of 6M short free-texts labeled as eligible or not eligible. A text classifier was trained using deep neural networks, with pre-trained word-embeddings as inputs, to predict whether or not short free-text statements describing clinical information were considered eligible. We additionally analyzed the semantic reasoning of the word-embedding representations obtained and were able to identify equivalent treatments for a type of tumor analogous with the drugs used to treat other tumors. We show that representation learning using deep neural networks can be successfully leveraged to extract the medical knowledge from clinical trial protocols for potentially assisting practitioners when prescribing treatments.
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.; Gil, P.; Pertusa, A.; Fisher, R. B.
Segmentation of Oil Spills on Side-Looking Airborne Radar Imagery with Autoencoders Journal Article
In: Sensors, vol. 18, no. 3, pp. 1424-8220, 2018, ISSN: 1424-8220.
@article{k385,
title = {Segmentation of Oil Spills on Side-Looking Airborne Radar Imagery with Autoencoders},
author = {A. J. Gallego and P. Gil and A. Pertusa and R. B. Fisher},
issn = {1424-8220},
year = {2018},
date = {2018-03-01},
journal = {Sensors},
volume = {18},
number = {3},
pages = {1424-8220},
abstract = {In this work, we use deep neural autoencoders to segment oil spills from Side-Looking Airborne Radar (SLAR) imagery. Synthetic Aperture Radar (SAR) has been much exploited for ocean surface monitoring, especially for oil pollution detection, but few approaches in the literature use SLAR. Our sensor consists of two SAR antennas mounted on an aircraft, enabling a quicker response than satellite sensors for emergency services when an oil spill occurs. Experiments on TERMA radar were carried out to detect oil spills on Spanish coasts using deep selectional autoencoders and RED-nets (very deep Residual Encoder-Decoder Networks). Different configurations of these networks were evaluated and the best topology significantly outperformed previous approaches, correctly detecting 100% of the spills and obtaining an F1 score of 93.01% at the pixel level. The proposed autoencoders perform accurately in SLAR imagery that has artifacts and noise caused by the aircraft maneuvers, in different weather conditions and with the presence of look-alikes due to natural phenomena such as shoals of fish and seaweed.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
In this work, we use deep neural autoencoders to segment oil spills from Side-Looking Airborne Radar (SLAR) imagery. Synthetic Aperture Radar (SAR) has been much exploited for ocean surface monitoring, especially for oil pollution detection, but few approaches in the literature use SLAR. Our sensor consists of two SAR antennas mounted on an aircraft, enabling a quicker response than satellite sensors for emergency services when an oil spill occurs. Experiments on TERMA radar were carried out to detect oil spills on Spanish coasts using deep selectional autoencoders and RED-nets (very deep Residual Encoder-Decoder Networks). Different configurations of these networks were evaluated and the best topology significantly outperformed previous approaches, correctly detecting 100% of the spills and obtaining an F1 score of 93.01% at the pixel level. The proposed autoencoders perform accurately in SLAR imagery that has artifacts and noise caused by the aircraft maneuvers, in different weather conditions and with the presence of look-alikes due to natural phenomena such as shoals of fish and seaweed.
Castellanos, F. J.; Valero-Mas, J. J.; Calvo-Zaragoza, J.; Rico-Juan, J. R.
Oversampling imbalanced data in the string space Journal Article
In: Pattern Recognition Letters, vol. 103, pp. 32–38, 2018, ISSN: 0167-8655.
Abstract | BibTeX | Tags: GRE16-14
@article{k382,
title = {Oversampling imbalanced data in the string space},
author = {F. J. Castellanos and J. J. Valero-Mas and J. Calvo-Zaragoza and J. R. Rico-Juan},
issn = {0167-8655},
year = {2018},
date = {2018-02-01},
journal = {Pattern Recognition Letters},
volume = {103},
pages = {32--38},
abstract = {Imbalanced data is a typical problem in the supervised classification field, which occurs when the different classes are not equally represented. This fact typically results in the classifier biasing its performance towards the class representing the majority of the elements. Many methods have been proposed to alleviate this scenario, yet all of them assume that data is represented as feature vectors. In this paper we propose a strategy to balance a dataset whose samples are encoded as strings. Our approach is based on adapting the well-known Synthetic Minority Over-sampling Technique (SMOTE) algorithm to the string space. More precisely, data generation is achieved with an iterative approach to create artificial strings within the segment between two given samples of the training set. Results with several datasets and imbalance ratios show that the proposed strategy properly deals with the problem in all cases considered.},
keywords = {GRE16-14},
pubstate = {published},
tppubtype = {article}
}
Imbalanced data is a typical problem in the supervised classification field, which occurs when the different classes are not equally represented. This fact typically results in the classifier biasing its performance towards the class representing the majority of the elements. Many methods have been proposed to alleviate this scenario, yet all of them assume that data is represented as feature vectors. In this paper we propose a strategy to balance a dataset whose samples are encoded as strings. Our approach is based on adapting the well-known Synthetic Minority Over-sampling Technique (SMOTE) algorithm to the string space. More precisely, data generation is achieved with an iterative approach to create artificial strings within the segment between two given samples of the training set. Results with several datasets and imbalance ratios show that the proposed strategy properly deals with the problem in all cases considered.
Gallego, A. J.; López, D.; Calera-Rubio, J.
Grammatical inference of directed acyclic graph languages with polynomial time complexity Journal Article
In: Journal of Computer and System Sciences, vol. 95, pp. 19-34, 2018, ISSN: 0022-0000.
@article{k514,
title = {Grammatical inference of directed acyclic graph languages with polynomial time complexity},
author = {A. J. Gallego and D. López and J. Calera-Rubio},
issn = {0022-0000},
year = {2018},
date = {2018-01-01},
journal = {Journal of Computer and System Sciences},
volume = {95},
pages = {19-34},
abstract = {In this paper we study the learning of graph languages. We extend the well-known classes of k-testability and k-testability in the strict sense languages to directed graph languages. We propose a grammatical inference algorithm to learn the class of directed acyclic k-testable in the strict sense graph languages. The algorithm runs in polynomial time and identifies this class of languages from positive data. We study its efficiency under several criteria, and perform a comprehensive experimentation with four datasets to show the validity of the method. Many fields, from pattern recognition to data compression, can take advantage of these results.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
In this paper we study the learning of graph languages. We extend the well-known classes of k-testability and k-testability in the strict sense languages to directed graph languages. We propose a grammatical inference algorithm to learn the class of directed acyclic k-testable in the strict sense graph languages. The algorithm runs in polynomial time and identifies this class of languages from positive data. We study its efficiency under several criteria, and perform a comprehensive experimentation with four datasets to show the validity of the method. Many fields, from pattern recognition to data compression, can take advantage of these results.
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}
}
Valero-Mas, J. J.; Benetos, E.; Iñesta, J. M.
A supervised classification approach for note tracking in polyphonic piano transcription Journal Article
In: Journal of New Music Research, vol. 47, no. 3, pp. 249–263, 2018, ISSN: 0929-8215.
Abstract | BibTeX | Tags: HispaMus
@article{k408,
title = {A supervised classification approach for note tracking in polyphonic piano transcription},
author = {J. J. Valero-Mas and E. Benetos and J. M. Iñesta},
issn = {0929-8215},
year = {2018},
date = {2018-01-01},
journal = {Journal of New Music Research},
volume = {47},
number = {3},
pages = {249--263},
abstract = {In the field of Automatic Music Transcription, note tracking systems constitute a key process in the overall success of the task as they compute the expected note-level abstraction out of a frame-based pitch activation representation. Despite its relevance, note tracking is most commonly performed using a set of hand-crafted rules adjusted in a manual fashion for the data at issue. In this regard, the present work introduces an approach based on machine learning, and more precisely supervised classification, that aims at automatically inferring such policies for the case of piano music. The idea is to segment each pitch band of a frame-based pitch activation into single instances which are subsequently classified as active or non-active note events. Results using a comprehensive set of supervised classification strategies on the MAPS piano data-set report its competitiveness against other commonly considered strategies for note tracking as well as an improvement of more than +10% in terms of F-measure when compared to the baseline considered for both frame-level and note-level evaluations.},
keywords = {HispaMus},
pubstate = {published},
tppubtype = {article}
}
In the field of Automatic Music Transcription, note tracking systems constitute a key process in the overall success of the task as they compute the expected note-level abstraction out of a frame-based pitch activation representation. Despite its relevance, note tracking is most commonly performed using a set of hand-crafted rules adjusted in a manual fashion for the data at issue. In this regard, the present work introduces an approach based on machine learning, and more precisely supervised classification, that aims at automatically inferring such policies for the case of piano music. The idea is to segment each pitch band of a frame-based pitch activation into single instances which are subsequently classified as active or non-active note events. Results using a comprehensive set of supervised classification strategies on the MAPS piano data-set report its competitiveness against other commonly considered strategies for note tracking as well as an improvement of more than +10% in terms of F-measure when compared to the baseline considered for both frame-level and note-level evaluations.
Rizo, D.; Pascual-León, N.; Sapp, C. S.
White Mensural Manual Encoding: from Humdrum to MEI Journal Article
In: Cuadernos de Investigación Musical, no. 6, pp. 373-393, 2018, ISSN: Cuadernos de Investigación Music.
Links | BibTeX | Tags: HispaMus
@article{k403,
title = {White Mensural Manual Encoding: from Humdrum to MEI},
author = {D. Rizo and N. Pascual-León and C. S. Sapp},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/403/1953-8089-1-PB.pdf},
issn = {Cuadernos de Investigación Music},
year = {2018},
date = {2018-01-01},
journal = {Cuadernos de Investigación Musical},
number = {6},
pages = {373-393},
keywords = {HispaMus},
pubstate = {published},
tppubtype = {article}
}
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.
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.
norm on neural codes is statistically beneficial for this approach.
Gallego, A. J.; Pertusa, A.; Gil, P.
Automatic Ship Classification from Optical Aerial Images with Convolutional Neural Networks Journal Article
In: Remote Sensing, vol. 10, no. 4, pp. 20, 2018, ISSN: 2072-4292.
@article{k388,
title = {Automatic Ship Classification from Optical Aerial Images with Convolutional Neural Networks},
author = {A. J. Gallego and A. Pertusa and P. Gil},
issn = {2072-4292},
year = {2018},
date = {2018-01-01},
journal = {Remote Sensing},
volume = {10},
number = {4},
pages = {20},
abstract = {The automatic classification of ships from aerial images is a considerable challenge. Previous works have usually applied image processing and computer vision techniques to extract meaningful features from visible spectrum images in order to use them as the input for traditional supervised classifiers. We present a method for determining if an aerial image of visible spectrum contains a ship or not. The proposed architecture is based on Convolutional Neural Networks (CNN), and it combines neural codes extracted from a CNN with a k-Nearest Neighbor method so as to improve performance. The kNN results are compared to those obtained with the CNN Softmax output. Several CNN models have been configured and evaluated in order to seek the best hyperparameters, and the most suitable setting for this task was found by using transfer learning at different levels. A new dataset (named MASATI) composed of aerial imagery with more than 6000 samples has also been created to train and evaluate our architecture. The experimentation shows a success rate of over 99% for our approach, in contrast with the 79% obtained with traditional methods in classification of ship images, also outperforming other methods based on CNNs. A dataset of images (MWPU VHR-10) used in previous works was additionally used to evaluate the proposed approach. Our best setup achieves a success ratio of 86% with these data, significantly outperforming previous state-of-the-art ship classification methods.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
The automatic classification of ships from aerial images is a considerable challenge. Previous works have usually applied image processing and computer vision techniques to extract meaningful features from visible spectrum images in order to use them as the input for traditional supervised classifiers. We present a method for determining if an aerial image of visible spectrum contains a ship or not. The proposed architecture is based on Convolutional Neural Networks (CNN), and it combines neural codes extracted from a CNN with a k-Nearest Neighbor method so as to improve performance. The kNN results are compared to those obtained with the CNN Softmax output. Several CNN models have been configured and evaluated in order to seek the best hyperparameters, and the most suitable setting for this task was found by using transfer learning at different levels. A new dataset (named MASATI) composed of aerial imagery with more than 6000 samples has also been created to train and evaluate our architecture. The experimentation shows a success rate of over 99% for our approach, in contrast with the 79% obtained with traditional methods in classification of ship images, also outperforming other methods based on CNNs. A dataset of images (MWPU VHR-10) used in previous works was additionally used to evaluate the proposed approach. Our best setup achieves a success ratio of 86% with these data, significantly outperforming previous state-of-the-art ship classification methods.
Iñesta, J. M.; Conklin, D.; Ramírez, R.; Fiore, T. M. M.
Machine Learning and Music Generation Book
Routledge, Taylor & Francis, 2018, ISBN: 978-0-8153-7720-7.
@book{k384,
title = {Machine Learning and Music Generation},
author = {J. M. Iñesta and D. Conklin and R. Ramírez and T. M. M. Fiore},
editor = {Thomas M. Fiore},
isbn = {978-0-8153-7720-7},
year = {2018},
date = {2018-01-01},
urldate = {2018-01-01},
pages = {111},
publisher = {Routledge, Taylor & Francis},
keywords = {TIMuL},
pubstate = {published},
tppubtype = {book}
}
Gallego, A. J.; Calvo-Zaragoza, J.; Valero-Mas, J. J.; Rico-Juan, J. R.
Clustering-based k-nearest neighbor classification for large-scale data with neural codes representation Journal Article
In: Pattern Recognition, vol. 74, pp. 531-543, 2018.
@article{k378,
title = {Clustering-based k-nearest neighbor classification for large-scale data with neural codes representation},
author = {A. J. Gallego and J. Calvo-Zaragoza and J. J. Valero-Mas and J. R. Rico-Juan},
year = {2018},
date = {2018-01-01},
urldate = {2018-01-01},
journal = {Pattern Recognition},
volume = {74},
pages = {531-543},
keywords = {TIMuL},
pubstate = {published},
tppubtype = {article}
}
Pertusa, A.; Gallego, A. J.; Bernabeu, M.
MirBot: A collaborative object recognition system for smartphones using convolutional neural networks Journal Article
In: Neurocomputing, vol. 293, pp. 87-99, 2018, ISSN: 0925-2312.
Abstract | BibTeX | Tags: TIMuL
@article{k366,
title = {MirBot: A collaborative object recognition system for smartphones using convolutional neural networks},
author = {A. Pertusa and A. J. Gallego and M. Bernabeu},
issn = {0925-2312},
year = {2018},
date = {2018-01-01},
urldate = {2018-01-01},
journal = {Neurocomputing},
volume = {293},
pages = {87-99},
abstract = {MirBot is a collaborative application for smartphones that allows users to perform object recognition. This app can be used to take a photograph of an object, select the region of interest and obtain the most likely class (dog, chair, etc.) by means of similarity search using features extracted from a convolutional neural network (CNN). The answers provided by the system can be validated by the user so as to improve the results for future queries. All the images are stored together with a series of metadata, thus enabling a multimodal incremental dataset labeled with synset identifiers from the WordNet ontology. This dataset grows continuously thanks to the users' feedback, and is publicly available for research. This work details the MirBot object recognition system, analyzes the statistics gathered after more than four years of usage, describes the image classification methodology, and performs an exhaustive evaluation using handcrafted features, neural codes, different transfer learning techniques, PCA compression and metadata, which can be used to improve the image classifier results. The app is freely available at the Apple and Google Play stores.},
keywords = {TIMuL},
pubstate = {published},
tppubtype = {article}
}
MirBot is a collaborative application for smartphones that allows users to perform object recognition. This app can be used to take a photograph of an object, select the region of interest and obtain the most likely class (dog, chair, etc.) by means of similarity search using features extracted from a convolutional neural network (CNN). The answers provided by the system can be validated by the user so as to improve the results for future queries. All the images are stored together with a series of metadata, thus enabling a multimodal incremental dataset labeled with synset identifiers from the WordNet ontology. This dataset grows continuously thanks to the users' feedback, and is publicly available for research. This work details the MirBot object recognition system, analyzes the statistics gathered after more than four years of usage, describes the image classification methodology, and performs an exhaustive evaluation using handcrafted features, neural codes, different transfer learning techniques, PCA compression and metadata, which can be used to improve the image classifier results. The app is freely available at the Apple and Google Play stores.
2017
Sober-Mira, J.; Calvo-Zaragoza, J.; Rizo, D.; Iñesta, J. M.
Pen-based music document transcription Proceedings Article
In: Proceedings of GREC 2017, pp. 21–22, IEEE computer society, Kyoto (Japan), 2017, ISBN: 978-1-5386-3586-5.
@inproceedings{k381,
title = {Pen-based music document transcription},
author = {J. Sober-Mira and J. Calvo-Zaragoza and D. Rizo and J. M. Iñesta},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/381/3586c021.pdf},
isbn = {978-1-5386-3586-5},
year = {2017},
date = {2017-11-01},
booktitle = {Proceedings of GREC 2017},
pages = {21--22},
publisher = {IEEE computer society},
address = {Kyoto (Japan)},
keywords = {TIMuL},
pubstate = {published},
tppubtype = {inproceedings}
}
Calvo-Zaragoza, J.; Gallego, A. J.; Pertusa, A.
Recognition of Handwritten Music Symbols with Convolutional Neural Codes Proceedings Article
In: 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), pp. 691–696, Kyoto, Japan, 2017.
BibTeX | Tags: GRE16-14, TIMuL
@inproceedings{k376,
title = {Recognition of Handwritten Music Symbols with Convolutional Neural Codes},
author = {J. Calvo-Zaragoza and A. J. Gallego and A. Pertusa},
year = {2017},
date = {2017-11-01},
urldate = {2017-11-01},
booktitle = {14th IAPR International Conference on Document Analysis and Recognition (ICDAR)},
pages = {691--696},
address = {Kyoto, Japan},
keywords = {GRE16-14, TIMuL},
pubstate = {published},
tppubtype = {inproceedings}
}
Sober-Mira, J.; Calvo-Zaragoza, J.; Rizo, D.; Iñesta, J. M.
Multimodal Recognition for Music Document Transcription Proceedings Article
In: Proceedings of MML 2017, pp. 67–72, Barcelona, 2017.
@inproceedings{k380,
title = {Multimodal Recognition for Music Document Transcription},
author = {J. Sober-Mira and J. Calvo-Zaragoza and D. Rizo and J. M. Iñesta},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/380/mml17proceedings-67.pdf},
year = {2017},
date = {2017-10-01},
booktitle = {Proceedings of MML 2017},
pages = {67--72},
address = {Barcelona},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Hontanilla, M.; Pérez-Sancho, C.; Iñesta, J. M.
Music style recognition with language models -- beyond statistical results Proceedings Article
In: Proceedings of MML 2017, pp. 31–36, Barcelona, 2017.
@inproceedings{k379,
title = {Music style recognition with language models -- beyond statistical results},
author = {M. Hontanilla and C. Pérez-Sancho and J. M. Iñesta},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/379/mml17proceedings-35.pdf},
year = {2017},
date = {2017-10-01},
booktitle = {Proceedings of MML 2017},
pages = {31--36},
address = {Barcelona},
keywords = {TIMuL},
pubstate = {published},
tppubtype = {inproceedings}
}
Calvo-Zaragoza, J.; Valero-Mas, J. J.; Pertusa, A
End-To-End Optical Music Recognition using Neural Networks Proceedings Article
In: Proc. of International Society for Music Information Retrieval Conference (ISMIR), Suzhou, China, 2017.
Abstract | BibTeX | Tags: GRE16-14, TIMuL
@inproceedings{k374,
title = {End-To-End Optical Music Recognition using Neural Networks},
author = {J. Calvo-Zaragoza and J. J. Valero-Mas and A Pertusa},
year = {2017},
date = {2017-10-01},
booktitle = {Proc. of International Society for Music Information Retrieval Conference (ISMIR)},
address = {Suzhou, China},
abstract = {This work addresses the Optical Music Recognition (OMR) task in an end-to-end fashion using neural net- works. The proposed architecture is based on a Recurrent Convolutional Neural Network topology that takes as input an image of a monophonic score and retrieves a sequence of music symbols as output. In the first stage, a series of convolutional filters are trained to extract meaningful fea- tures of the input image, and then a recurrent block models the sequential nature of music. The system is trained us- ing a Connectionist Temporal Classification loss function, which avoids the need for a frame-by-frame alignment be- tween the image and the ground-truth music symbols. Ex- perimentation has been carried on a set of 90,000 synthetic monophonic music scores with more than 50 different pos- sible labels. Results obtained depict classification error rates around 2 % at symbol level, thus proving the po- tential of the proposed end-to-end architecture for OMR. The source code, dataset, and trained models are publicly released for reproducible research and future comparison purposes.},
keywords = {GRE16-14, TIMuL},
pubstate = {published},
tppubtype = {inproceedings}
}
This work addresses the Optical Music Recognition (OMR) task in an end-to-end fashion using neural net- works. The proposed architecture is based on a Recurrent Convolutional Neural Network topology that takes as input an image of a monophonic score and retrieves a sequence of music symbols as output. In the first stage, a series of convolutional filters are trained to extract meaningful fea- tures of the input image, and then a recurrent block models the sequential nature of music. The system is trained us- ing a Connectionist Temporal Classification loss function, which avoids the need for a frame-by-frame alignment be- tween the image and the ground-truth music symbols. Ex- perimentation has been carried on a set of 90,000 synthetic monophonic music scores with more than 50 different pos- sible labels. Results obtained depict classification error rates around 2 % at symbol level, thus proving the po- tential of the proposed end-to-end architecture for OMR. The source code, dataset, and trained models are publicly released for reproducible research and future comparison purposes.
Alacid, B.; Gallego, A. J.; Gil, P.; Pertusa, A.
Oil Slicks Detection in SLAR Images with Autoencoders Proceedings Article
In: 5th International Symposium on Sensor Science, Barcelona, Spain, 2017.
@inproceedings{k375,
title = {Oil Slicks Detection in SLAR Images with Autoencoders},
author = {B. Alacid and A. J. Gallego and P. Gil and A. Pertusa},
year = {2017},
date = {2017-09-01},
urldate = {2017-09-01},
booktitle = {5th International Symposium on Sensor Science},
address = {Barcelona, Spain},
keywords = {ENJAMBRE},
pubstate = {published},
tppubtype = {inproceedings}
}
Bernabeu, J. F.
Similarity Learning and Stochastic Language Models for Tree-Represented Music PhD Thesis
2017.
@phdthesis{k377,
title = {Similarity Learning and Stochastic Language Models for Tree-Represented Music},
author = {J. F. Bernabeu},
editor = {José M. Iñesta and J. Calera-Rubio},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/377/BernabeuPhD.pdf},
year = {2017},
date = {2017-07-01},
organization = {University of Alicante},
keywords = {TIMuL},
pubstate = {published},
tppubtype = {phdthesis}
}
Valero-Mas, J. J.
Towards Interactive Multimodal Music Transcription PhD Thesis
2017.
@phdthesis{k371,
title = {Towards Interactive Multimodal Music Transcription},
author = {J. J. Valero-Mas},
editor = {José M. Iñesta},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/371/Thesis.pdf},
year = {2017},
date = {2017-07-01},
urldate = {2017-07-01},
organization = {University of Alicante},
keywords = {TIMuL},
pubstate = {published},
tppubtype = {phdthesis}
}
Valero-Mas, J. J.; Iñesta, J. M.
Experimental assessment of descriptive statistics and adaptive methodologies for threshold establishment in onset selection functions Proceedings Article
In: Proceedings of the 14th Sound and Music Computing Conference (SMC), pp. 117–124, Espoo (Finland), 2017.
@inproceedings{k368,
title = {Experimental assessment of descriptive statistics and adaptive methodologies for threshold establishment in onset selection functions},
author = {J. J. Valero-Mas and J. M. Iñesta},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/368/CameraReady.pdf},
year = {2017},
date = {2017-07-01},
booktitle = {Proceedings of the 14th Sound and Music Computing Conference (SMC)},
pages = {117--124},
address = {Espoo (Finland)},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Valero-Mas, J. J.; Benetos, E.; Iñesta, J. M.
Assessing the Relevance of Onset Information for Note Tracking in Piano Music Transcription Proceedings Article
In: Proceedings of the AES International Conference on Semantic Audio, Eerlangen, 2017.
@inproceedings{k363,
title = {Assessing the Relevance of Onset Information for Note Tracking in Piano Music Transcription},
author = {J. J. Valero-Mas and E. Benetos and J. M. Iñesta},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/363/CameraReady.pdf},
year = {2017},
date = {2017-06-21},
booktitle = {Proceedings of the AES International Conference on Semantic Audio},
address = {Eerlangen},
keywords = {TIMuL},
pubstate = {published},
tppubtype = {inproceedings}
}
Valero-Mas, J. J.; Calvo-Zaragoza, J.; Rico-Juan, J. R.; Iñesta, J. M.
A study of Prototype Selection algorithms for Nearest Neighbour in class-imbalanced problems Proceedings Article
In: Alexandre, J. S. Sánchez L. A.; Rodrigues, J. M. F. (Ed.): Proceedings of the 8th Iberian Conference on Pattern Recognition and Image Analysis (IbPRIA), pp. 335–343, Springer, Faro, Portugal, 2017, ISBN: 978-3-319-58837-7.
@inproceedings{k362,
title = {A study of Prototype Selection algorithms for Nearest Neighbour in class-imbalanced problems},
author = {J. J. Valero-Mas and J. Calvo-Zaragoza and J. R. Rico-Juan and J. M. Iñesta},
editor = {J. S. Sánchez L. A. Alexandre and J. M. F. Rodrigues},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/362/CameraReady.pdf},
isbn = {978-3-319-58837-7},
year = {2017},
date = {2017-06-01},
booktitle = {Proceedings of the 8th Iberian Conference on Pattern Recognition and Image Analysis (IbPRIA)},
pages = {335--343},
publisher = {Springer},
address = {Faro, Portugal},
keywords = {TIMuL},
pubstate = {published},
tppubtype = {inproceedings}
}
Rizo, D.; Calvo-Zaragoza, J.; Iñesta, J. M.; Fujinaga, I.
About agnostic representation of musical documents for Optical Music Recognition Proceedings Article
In: Music Encoding Conference, Tours, 2017, 2017.
@inproceedings{k369,
title = {About agnostic representation of musical documents for Optical Music Recognition},
author = {D. Rizo and J. Calvo-Zaragoza and J. M. Iñesta and I. Fujinaga},
year = {2017},
date = {2017-05-01},
booktitle = {Music Encoding Conference, Tours, 2017},
keywords = {TIMuL},
pubstate = {published},
tppubtype = {inproceedings}
}
Calvo-Zaragoza, J.; Oncina, J.
An efficient approach for Interactive Sequential Pattern Recognition Journal Article
In: Pattern Recognition, vol. 64, pp. 295-304, 2017.
@article{k359,
title = {An efficient approach for Interactive Sequential Pattern Recognition},
author = {J. Calvo-Zaragoza and J. Oncina},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/359/efficient-approach-sequential.pdf},
year = {2017},
date = {2017-04-01},
journal = {Pattern Recognition},
volume = {64},
pages = {295-304},
keywords = {TIMuL},
pubstate = {published},
tppubtype = {article}
}
Calvo-Zaragoza, J.; Oncina, J.
Recognition of Pen-based Music Notation with Finite-State Machines Journal Article
In: Expert Systems With Applications, vol. 72, pp. 395-406, 2017.
@article{k358,
title = {Recognition of Pen-based Music Notation with Finite-State Machines},
author = {J. Calvo-Zaragoza and J. Oncina},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/358/recognition-pen-based.pdf},
year = {2017},
date = {2017-04-01},
journal = {Expert Systems With Applications},
volume = {72},
pages = {395-406},
keywords = {TIMuL},
pubstate = {published},
tppubtype = {article}
}
Rizo, D.; Pascual, B.; Iñesta, J. M.; González, L. A.; Ezquerro, A.
Towards the Digital Encoding of Hispanic White Mensural Notation Journal Article
In: Anuario Musical, no. 72, pp. 293–304, 2017, ISSN: 0211-3538.
Abstract | BibTeX | Tags: TIMuL
@article{k383,
title = {Towards the Digital Encoding of Hispanic White Mensural Notation},
author = {D. Rizo and B. Pascual and J. M. Iñesta and L. A. González and A. Ezquerro},
issn = {0211-3538},
year = {2017},
date = {2017-01-01},
urldate = {2017-01-01},
journal = {Anuario Musical},
number = {72},
pages = {293--304},
abstract = {In this work, the elements necessary for digitally encoding music contained in manuscripts from the centuries 16th to 17th are introduced. The solutions proposed to overcome the difficulties that generate some of the aspects that make this notation different from the modern Western notation are presented. Problems faced are, for example, the absence of bar lines or the duration of notes that are based on the context. The new typographic font 'Capitán', created specifically to represent this type of early notation, is also presented.},
keywords = {TIMuL},
pubstate = {published},
tppubtype = {article}
}
In this work, the elements necessary for digitally encoding music contained in manuscripts from the centuries 16th to 17th are introduced. The solutions proposed to overcome the difficulties that generate some of the aspects that make this notation different from the modern Western notation are presented. Problems faced are, for example, the absence of bar lines or the duration of notes that are based on the context. The new typographic font 'Capitán', created specifically to represent this type of early notation, is also presented.
Gallego, A. J.; Calvo-Zaragoza, J.
Staff-line removal with Selectional Auto-Encoders Journal Article
In: Expert Systems With Applications, vol. 89, pp. 138 - 148, 2017, ISSN: 0957-4174.
Abstract | Links | BibTeX | Tags: TIMuL
@article{k372,
title = {Staff-line removal with Selectional Auto-Encoders},
author = {A. J. Gallego and J. Calvo-Zaragoza},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/372/staff-line-removal.pdf},
issn = {0957-4174},
year = {2017},
date = {2017-01-01},
urldate = {2017-01-01},
journal = {Expert Systems With Applications},
volume = {89},
pages = {138 - 148},
abstract = {Staff-line removal is an important preprocessing stage as regards most Optical Music Recognition systems. The common procedures employed to carry out this task involve image processing techniques. In contrast to these traditional methods, which are based on hand-engineered transformations, the problem can also be approached from a machine learning point of view if representative examples of the task are provided. We propose doing this through the use of a new approach involving auto-encoders, which select the appropriate features of an input feature set (Selectional Auto-Encoders). Within the context of the problem at hand, the model is trained to select those pixels of a given image that belong to a musical symbol, thus removing the lines of the staves. Our results show that the proposed technique is quite competitive and significantly outperforms the other state-of-art strategies considered, particularly when dealing with grayscale input images.},
keywords = {TIMuL},
pubstate = {published},
tppubtype = {article}
}
Staff-line removal is an important preprocessing stage as regards most Optical Music Recognition systems. The common procedures employed to carry out this task involve image processing techniques. In contrast to these traditional methods, which are based on hand-engineered transformations, the problem can also be approached from a machine learning point of view if representative examples of the task are provided. We propose doing this through the use of a new approach involving auto-encoders, which select the appropriate features of an input feature set (Selectional Auto-Encoders). Within the context of the problem at hand, the model is trained to select those pixels of a given image that belong to a musical symbol, thus removing the lines of the staves. Our results show that the proposed technique is quite competitive and significantly outperforms the other state-of-art strategies considered, particularly when dealing with grayscale input images.
Valero-Mas, J. J.; Iñesta, J. M.
Interactive User Correction of Automatically Detected Onsets: Approach and Evaluation Journal Article
In: EURASIP Journal on Audio, Speech, and Music Processing, no. 15, 2017, ISSN: 1687-4722.
@article{k367,
title = {Interactive User Correction of Automatically Detected Onsets: Approach and Evaluation},
author = {J. J. Valero-Mas and J. M. Iñesta},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/367/EURASIP_Valero-MasInesta-2017.pdf},
issn = {1687-4722},
year = {2017},
date = {2017-01-01},
journal = {EURASIP Journal on Audio, Speech, and Music Processing},
number = {15},
keywords = {TIMuL},
pubstate = {published},
tppubtype = {article}
}
Calvo-Zaragoza, J.; Pertusa, A.; Oncina, J.
Staff-line detection and removal using a convolutional neural network Journal Article
In: Machine Vision and Applications, pp. 1-10, 2017, ISSN: 1432-1769.
Abstract | BibTeX | Tags: TIMuL
@article{k365,
title = {Staff-line detection and removal using a convolutional neural network},
author = {J. Calvo-Zaragoza and A. Pertusa and J. Oncina},
issn = {1432-1769},
year = {2017},
date = {2017-01-01},
urldate = {2017-01-01},
journal = {Machine Vision and Applications},
pages = {1-10},
abstract = {Staff-line removal is an important preprocessing stage for most optical music recognition systems. Common procedures to solve this task involve image processing techniques. In contrast to these traditional methods based on hand-engineered transformations, the problem can also be approached as a classification task in which each pixel is labeled as either staff or symbol, so that only those that belong to symbols are kept in the image. In order to perform this classification, we propose the use of convolutional neural networks, which have demonstrated an outstanding performance in image retrieval tasks. The initial features of each pixel consist of a square patch from the input image centered at that pixel. The proposed network is trained by using a dataset which contains pairs of scores with and without the staff lines. Our results in both binary and grayscale images show that the proposed technique is very accurate, outperforming both other classifiers and the state-of-the-art strategies considered. In addition, several advantages of the presented methodology with respect to traditional procedures proposed so far are discussed.},
keywords = {TIMuL},
pubstate = {published},
tppubtype = {article}
}
Staff-line removal is an important preprocessing stage for most optical music recognition systems. Common procedures to solve this task involve image processing techniques. In contrast to these traditional methods based on hand-engineered transformations, the problem can also be approached as a classification task in which each pixel is labeled as either staff or symbol, so that only those that belong to symbols are kept in the image. In order to perform this classification, we propose the use of convolutional neural networks, which have demonstrated an outstanding performance in image retrieval tasks. The initial features of each pixel consist of a square patch from the input image centered at that pixel. The proposed network is trained by using a dataset which contains pairs of scores with and without the staff lines. Our results in both binary and grayscale images show that the proposed technique is very accurate, outperforming both other classifiers and the state-of-the-art strategies considered. In addition, several advantages of the presented methodology with respect to traditional procedures proposed so far are discussed.
Calvo-Zaragoza, J.; Vigliensoni, G.; Fujinaga, I.
Pixel-wise Binarization of Musical Documents with Convolutional Neural Networks Proceedings Article
In: Proceedings of the 15th IAPR International Conference on Machine Vision Applications, 2017.
@inproceedings{k361,
title = {Pixel-wise Binarization of Musical Documents with Convolutional Neural Networks},
author = {J. Calvo-Zaragoza and G. Vigliensoni and I. Fujinaga},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/361/pixel-wise-binarization.pdf},
year = {2017},
date = {2017-01-01},
booktitle = {Proceedings of the 15th IAPR International Conference on Machine Vision Applications},
keywords = {TIMuL},
pubstate = {published},
tppubtype = {inproceedings}
}
Calvo-Zaragoza, J.; Vigliensoni, G.; Fujinaga, I.
A machine learning framework for the categorization of elements in images of musical documents Proceedings Article
In: Proceedings of the Third International Conference on Technologies for Music Notation and Representation, 2017.
@inproceedings{k360,
title = {A machine learning framework for the categorization of elements in images of musical documents},
author = {J. Calvo-Zaragoza and G. Vigliensoni and I. Fujinaga},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/360/tenor-unified-categorization.pdf},
year = {2017},
date = {2017-01-01},
booktitle = {Proceedings of the Third International Conference on Technologies for Music Notation and Representation},
keywords = {TIMuL},
pubstate = {published},
tppubtype = {inproceedings}
}
Valero-Mas, J. J.; Calvo-Zaragoza, J.; Rico-Juan, J. R.; Iñesta, J. M.
An Experimental Study on Rank Methods for Prototype Selection Journal Article
In: Soft Computing, vol. 21, no. 19, pp. 5703-–5715, 2017, ISSN: 1432-7643.
Abstract | Links | BibTeX | Tags: TIMuL
@article{k339,
title = {An Experimental Study on Rank Methods for Prototype Selection},
author = {J. J. Valero-Mas and J. Calvo-Zaragoza and J. R. Rico-Juan and J. M. Iñesta},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/339/SOCO-RankMethods-2016.pdf},
issn = {1432-7643},
year = {2017},
date = {2017-01-01},
journal = {Soft Computing},
volume = {21},
number = {19},
pages = {5703-–5715},
abstract = {Prototype selection is one of the most popular approaches for addressing the low efficiency issue typically found in the well-known k-Nearest Neighbour classification rule. These techniques select a representative subset from an original collection of prototypes with the premise of main- taining the same classification accuracy. Most recently, rank methods have been proposed as an alternative to develop new selection strategies. Following a certain heuristic, these methods sort the elements of the initial collection accord- ing to their relevance and then select the best possible subset by means of a parameter representing the amount of data to maintain. Due to the relative novelty of these methods, their performance and competitiveness against other strategies is still unclear. This work performs an exhaustive experimental study of such methods for prototype selection. A represen- tative collection of both classic and sophisticated algorithms are compared to the aforementioned techniques in a num- ber of datasets, including different levels of induced noise. Results report the remarkable competitiveness of these rank methods as well as their excellent trade-off between proto- type reduction and achieved accuracy.},
keywords = {TIMuL},
pubstate = {published},
tppubtype = {article}
}
Prototype selection is one of the most popular approaches for addressing the low efficiency issue typically found in the well-known k-Nearest Neighbour classification rule. These techniques select a representative subset from an original collection of prototypes with the premise of main- taining the same classification accuracy. Most recently, rank methods have been proposed as an alternative to develop new selection strategies. Following a certain heuristic, these methods sort the elements of the initial collection accord- ing to their relevance and then select the best possible subset by means of a parameter representing the amount of data to maintain. Due to the relative novelty of these methods, their performance and competitiveness against other strategies is still unclear. This work performs an exhaustive experimental study of such methods for prototype selection. A represen- tative collection of both classic and sophisticated algorithms are compared to the aforementioned techniques in a num- ber of datasets, including different levels of induced noise. Results report the remarkable competitiveness of these rank methods as well as their excellent trade-off between proto- type reduction and achieved accuracy.
2016
Bellet, A.; Bernabeu, J. F.; Habrard, A.; Sebban, M.
Learning discriminative tree edit similarities for linear classification - Application to melody recognition Journal Article
In: Neurocomputing, vol. 214, pp. 155-161, 2016.
Abstract | Links | BibTeX | Tags: TIMuL
@article{k349,
title = {Learning discriminative tree edit similarities for linear classification - Application to melody recognition},
author = {A. Bellet and J. F. Bernabeu and A. Habrard and M. Sebban},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/349/ldTree2016.pdf},
year = {2016},
date = {2016-11-01},
urldate = {2016-11-01},
journal = {Neurocomputing},
volume = {214},
pages = {155-161},
abstract = {Similarity functions are a fundamental component of many learning algorithms. When dealing with string or tree-structured data, measures based on the edit distance are widely used, and there exist a few methods for learning them from data. In this context, we recently proposed GESL (Bellet et al., 2012 [3]), an approach to string edit similarity learning based on loss minimization which offers theoretical guarantees as to the generalization ability and discriminative power of the learned similarities. In this paper, we argue that GESL, which has been originally dedicated to deal with strings, can be extended to trees and lead to powerful and competitive similarities. We illustrate this claim on a music recognition task, namely melody classification, where each piece is represented as a tree modeling its structure as well as rhythm and pitch information. The results show that GESL outperforms standard as well as probabilistically-learned edit distances and that it is able to describe consistently the underlying melodic similarity model.},
keywords = {TIMuL},
pubstate = {published},
tppubtype = {article}
}
Similarity functions are a fundamental component of many learning algorithms. When dealing with string or tree-structured data, measures based on the edit distance are widely used, and there exist a few methods for learning them from data. In this context, we recently proposed GESL (Bellet et al., 2012 [3]), an approach to string edit similarity learning based on loss minimization which offers theoretical guarantees as to the generalization ability and discriminative power of the learned similarities. In this paper, we argue that GESL, which has been originally dedicated to deal with strings, can be extended to trees and lead to powerful and competitive similarities. We illustrate this claim on a music recognition task, namely melody classification, where each piece is represented as a tree modeling its structure as well as rhythm and pitch information. The results show that GESL outperforms standard as well as probabilistically-learned edit distances and that it is able to describe consistently the underlying melodic similarity model.
Iñesta, J. M.; Conklin, D.; Ramírez, R.
Machine learning and music generation Journal Article
In: Journal of Mathematics and Music, vol. 10, no. 2, pp. 87–91, 2016, ISSN: 1745-9737.
Abstract | Links | BibTeX | Tags:
@article{k357,
title = {Machine learning and music generation},
author = {J. M. Iñesta and D. Conklin and R. Ramírez},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/357/jmm2016-editorial.pdf},
issn = {1745-9737},
year = {2016},
date = {2016-10-01},
journal = {Journal of Mathematics and Music},
volume = {10},
number = {2},
pages = {87--91},
abstract = {Computational approaches to music composition and style imitation have engaged musicians, music scholars, and computer scientists since the early days of computing. Music generation research has generally employed one of two strategies: knowledge-based methods that model style through explicitly formalized rules, and data mining methods that apply machine learning to induce statistical models of musical style.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Computational approaches to music composition and style imitation have engaged musicians, music scholars, and computer scientists since the early days of computing. Music generation research has generally employed one of two strategies: knowledge-based methods that model style through explicitly formalized rules, and data mining methods that apply machine learning to induce statistical models of musical style.
Rizo, D.; Calvo-Zaragoza, J.; Iñesta, J. M.; Illescas, P. R.
Hidden Markov Models for Functional Analysis Proceedings Article
In: Music and Machine Learning Workshop, Riva del Garda, 2016.
@inproceedings{k370,
title = {Hidden Markov Models for Functional Analysis},
author = {D. Rizo and J. Calvo-Zaragoza and J. M. Iñesta and P. R. Illescas},
year = {2016},
date = {2016-09-01},
booktitle = {Music and Machine Learning Workshop, Riva del Garda},
keywords = {TIMuL},
pubstate = {published},
tppubtype = {inproceedings}
}
Valero-Mas, J. J.; Benetos, E.; Iñesta, J. M.
Classification-based Note Tracking for Automatic Music Transcription Proceedings Article
In: Proceedings of the 9th Machine Learning and Music Workshop (MML2016), pp. 61–65, European Conference on Machine Learning and Principles and Practice of Knowledge Discovery (ECML-PKDD) Riva del Garda, Italy, 2016.
@inproceedings{k352,
title = {Classification-based Note Tracking for Automatic Music Transcription},
author = {J. J. Valero-Mas and E. Benetos and J. M. Iñesta},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/352/ValeroMasBenetosInesta-MML2016.pdf},
year = {2016},
date = {2016-09-01},
booktitle = {Proceedings of the 9th Machine Learning and Music Workshop (MML2016)},
pages = {61--65},
address = {Riva del Garda, Italy},
organization = {European Conference on Machine Learning and Principles and Practice of Knowledge Discovery (ECML-PKDD)},
keywords = {TIMuL},
pubstate = {published},
tppubtype = {inproceedings}
}
Rizo, D.; Marsden, A.
A standard format proposal for hierarchical analyses and representations Proceedings Article
In: Proceedings of the 3rd International Workshop on Digital Libraries for Musicology, pp. 25–32, ACM, New York, USA, 2016, ISBN: 978-1-4503-4751-8.
Abstract | BibTeX | Tags: TIMuL
@inproceedings{k356,
title = {A standard format proposal for hierarchical analyses and representations},
author = {D. Rizo and A. Marsden},
isbn = {978-1-4503-4751-8},
year = {2016},
date = {2016-08-01},
booktitle = {Proceedings of the 3rd International Workshop on Digital Libraries for Musicology},
pages = {25--32},
publisher = {ACM},
address = {New York, USA},
abstract = {In the realm of digital musicology, standardizations efforts to date have mostly concentrated on the representation of music. Anal- yses of music are increasingly being generated or communicated by digital means. We demonstrate that the same arguments for the desirability of standardization in the representation of music apply also to the representation of analyses of music: proper preservation, sharing of data, and facilitation of digital processing. We concen- trate here on analyses which can be described as hierarchical and show that this covers a broad range of existing analytical formats. We propose an extension of MEI (Music Encoding Initiative) to al- low the encoding of analyses unambiguously associated with and aligned to a representation of the music analysed, making use of existing mechanisms within MEI’ and s parent TEI (Text Encoding Ini- tiative) for the representation of trees and graphs.},
keywords = {TIMuL},
pubstate = {published},
tppubtype = {inproceedings}
}
In the realm of digital musicology, standardizations efforts to date have mostly concentrated on the representation of music. Anal- yses of music are increasingly being generated or communicated by digital means. We demonstrate that the same arguments for the desirability of standardization in the representation of music apply also to the representation of analyses of music: proper preservation, sharing of data, and facilitation of digital processing. We concen- trate here on analyses which can be described as hierarchical and show that this covers a broad range of existing analytical formats. We propose an extension of MEI (Music Encoding Initiative) to al- low the encoding of analyses unambiguously associated with and aligned to a representation of the music analysed, making use of existing mechanisms within MEI’ and s parent TEI (Text Encoding Ini- tiative) for the representation of trees and graphs.
Calvo-Zaragoza, J.; Rizo, D.; Iñesta, J. M.
Two (note) heads are better than one: pen-based multimodal interaction with music scores Proceedings Article
In: Devaney, J. (Ed.): 17th International Society for Music Information Retrieval Conference, pp. 509-514, New York City, 2016, ISBN: 978-0-692-75506-8.
@inproceedings{k345,
title = {Two (note) heads are better than one: pen-based multimodal interaction with music scores},
author = {J. Calvo-Zaragoza and D. Rizo and J. M. Iñesta},
editor = {J. Devaney},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/345/two-note-heads.pdf},
isbn = {978-0-692-75506-8},
year = {2016},
date = {2016-08-01},
booktitle = {17th International Society for Music Information Retrieval Conference},
pages = {509-514},
address = {New York City},
keywords = {TIMuL},
pubstate = {published},
tppubtype = {inproceedings}
}
Valero-Mas, J. J.; Calvo-Zaragoza, J.; Rico-Juan, J. R.
On the suitability of Prototype Selection methods for kNN classification with distributed data Journal Article
In: Neurocomputing, vol. 203, pp. 150-160, 2016.
@article{k341,
title = {On the suitability of Prototype Selection methods for kNN classification with distributed data},
author = {J. J. Valero-Mas and J. Calvo-Zaragoza and J. R. Rico-Juan},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/341/SuitabilityPSDistributedScenarios.pdf},
year = {2016},
date = {2016-08-01},
journal = {Neurocomputing},
volume = {203},
pages = {150-160},
keywords = {TIMuL},
pubstate = {published},
tppubtype = {article}
}
Iñesta, J. M.; de León, P. J. Ponce
Data-based melody generation through multi-objective evolutionary computation Journal Article
In: Journal of Mathematics and Music, vol. 10, no. 2, pp. 173-192, 2016, ISSN: 1745-9737.
Abstract | Links | BibTeX | Tags: TIMuL
@article{k344,
title = {Data-based melody generation through multi-objective evolutionary computation},
author = {J. M. Iñesta and P. J. Ponce de León},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/344/Data+based+melody+generation+through+multi+objective+evolutionary+computation+%28post-print%29.pdf},
issn = {1745-9737},
year = {2016},
date = {2016-07-01},
urldate = {2016-07-01},
journal = {Journal of Mathematics and Music},
volume = {10},
number = {2},
pages = {173-192},
abstract = {Genetic-based composition algorithms are able to explore an immense space of possibilities, but the main difficulty has always been the implementation of the selection process. In this work, sets of melodies are utilized for training a machine learning approach to compute fitness, based on different metrics. The fitness of a candidate is provided by combining the metrics, but their values can range through different orders of magnitude and evolve in different ways, which makes it hard to combine these criteria. In order to solve this problem, a multi-objective fitness approach is proposed, in which the best individuals are those in the Pareto front of the multi-dimensional fitness space. Melodic trees are also proposed as a data structure for chromosomic representation of melodies and genetic operators are adapted to them. Some experiments have been carried out using a graphical interface prototype that allows one to explore the creative capabilities of the proposed system. An Online Supplement is provided and can be accessed at http://dx.doi.org/10.1080/17459737.2016.1188171, where the reader can find some technical details, information about the data used, generated melodies, and additional information about the developed prototype and its performance.},
keywords = {TIMuL},
pubstate = {published},
tppubtype = {article}
}
Genetic-based composition algorithms are able to explore an immense space of possibilities, but the main difficulty has always been the implementation of the selection process. In this work, sets of melodies are utilized for training a machine learning approach to compute fitness, based on different metrics. The fitness of a candidate is provided by combining the metrics, but their values can range through different orders of magnitude and evolve in different ways, which makes it hard to combine these criteria. In order to solve this problem, a multi-objective fitness approach is proposed, in which the best individuals are those in the Pareto front of the multi-dimensional fitness space. Melodic trees are also proposed as a data structure for chromosomic representation of melodies and genetic operators are adapted to them. Some experiments have been carried out using a graphical interface prototype that allows one to explore the creative capabilities of the proposed system. An Online Supplement is provided and can be accessed at http://dx.doi.org/10.1080/17459737.2016.1188171, where the reader can find some technical details, information about the data used, generated melodies, and additional information about the developed prototype and its performance.
Calvo-Zaragoza, J.; Oncina, J.; Higuera, C. De La
Computing the Expected Edit Distance from a String to a PFA Proceedings Article
In: Han, Yo-Sub; Salomaa, Kai (Ed.): 21st International Conference Implementation and Application of Automata, pp. 39-50, Springer, 2016.
@inproceedings{k342,
title = {Computing the Expected Edit Distance from a String to a PFA},
author = {J. Calvo-Zaragoza and J. Oncina and C. De La Higuera},
editor = {Yo-Sub Han and Kai Salomaa},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/342/distance-string-pfa.pdf},
year = {2016},
date = {2016-07-01},
urldate = {2016-07-01},
booktitle = {21st International Conference Implementation and Application of Automata},
pages = {39-50},
publisher = {Springer},
keywords = {TIMuL},
pubstate = {published},
tppubtype = {inproceedings}
}
Bernabeu, M.; Pertusa, A.; Gallego, A. J.
Image spatial verification using Segment Intersection of Interest Points Proceedings Article
In: Proc. of the 24 Int. Conf. in Central Europe on Computer Graphics, Visualization and Computer Vision (WSCG), 2016, ISBN: 2464-4614.
@inproceedings{k346,
title = {Image spatial verification using Segment Intersection of Interest Points},
author = {M. Bernabeu and A. Pertusa and A. J. Gallego},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/346/imageSpatialVerification.pdf},
isbn = {2464-4614},
year = {2016},
date = {2016-05-01},
booktitle = {Proc. of the 24 Int. Conf. in Central Europe on Computer Graphics, Visualization and Computer Vision (WSCG)},
keywords = {TIMuL},
pubstate = {published},
tppubtype = {inproceedings}
}
Rizo, D.; Illescas, P. R.; Iñesta, J. M.
Interactive melodic analysis Book Chapter
In: Meredith, D. (Ed.): Computational Music Analysis, Chapter 7, pp. 191-219, Springer, 2016, ISBN: 978-3-319-25931-4.
Abstract | Links | BibTeX | Tags: GRE-12-34, Prometeo 2012, TIMuL
@inbook{k322,
title = {Interactive melodic analysis},
author = {D. Rizo and P. R. Illescas and J. M. Iñesta},
editor = {D. Meredith},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/322/RizoEtAl.pdf},
isbn = {978-3-319-25931-4},
year = {2016},
date = {2016-01-01},
urldate = {2016-01-01},
booktitle = {Computational Music Analysis},
pages = {191-219},
publisher = {Springer},
chapter = {7},
abstract = {Melodic analysis sets the importance and role of each note in a particular harmonic context. Thus, a note is classified as a harmonic tone, when it belongs to the underlying chord, and as a non harmonic tone otherwise, with a number of categories in this latter case. Automatic systems for solving this task are still far from being available, so it must be assumed that in a practical scenario the human expert must correct the system’s output. Interactive systems allow for turning the user into a source of high-quality and high-confidence training data, so on-line ma- chine learning and interactive pattern recognition provide tools that have proven to be very convenient in this context.},
keywords = {GRE-12-34, Prometeo 2012, TIMuL},
pubstate = {published},
tppubtype = {inbook}
}
Melodic analysis sets the importance and role of each note in a particular harmonic context. Thus, a note is classified as a harmonic tone, when it belongs to the underlying chord, and as a non harmonic tone otherwise, with a number of categories in this latter case. Automatic systems for solving this task are still far from being available, so it must be assumed that in a practical scenario the human expert must correct the system’s output. Interactive systems allow for turning the user into a source of high-quality and high-confidence training data, so on-line ma- chine learning and interactive pattern recognition provide tools that have proven to be very convenient in this context.
Rizo, D.; Pascual, B.; Ezquerro, A.; Iñesta, J. M.; González, L. A.
Tipografía y transductor para la transcripción musical interactiva de notación mensural hispánica Proceedings Article
In: Libro de actas de las I jornadas sobre la investigación en los centros superiores de enseñanzas artísticas, pp. 6–23, ISEACV, Valencia, 2016, ISBN: 978-84-608-6758-6.
@inproceedings{k364,
title = {Tipografía y transductor para la transcripción musical interactiva de notación mensural hispánica},
author = {D. Rizo and B. Pascual and A. Ezquerro and J. M. Iñesta and L. A. González},
isbn = {978-84-608-6758-6},
year = {2016},
date = {2016-01-01},
urldate = {2016-01-01},
booktitle = {Libro de actas de las I jornadas sobre la investigación en los centros superiores de enseñanzas artísticas},
pages = {6--23},
publisher = {ISEACV},
address = {Valencia},
keywords = {TIMuL},
pubstate = {published},
tppubtype = {inproceedings}
}