2016
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.2015
Calvo-Zaragoza, J.; Barbancho, I.; Tardón, L. J.; Barbancho, A. M.
Avoiding staff removal stage in optical music recognition: application to scores written in white mensural notation Journal Article
In: Pattern Analysis and Applications, vol. 18, no. 4, pp. 933-943, 2015, ISSN: 1433-7541.
Links | BibTeX | Tags: Prometeo 2012, TIMuL
@article{k318,
title = {Avoiding staff removal stage in optical music recognition: application to scores written in white mensural notation},
author = {J. Calvo-Zaragoza and I. Barbancho and L. J. Tardón and A. M. Barbancho},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/318/paaa-jcalvo.pdf},
issn = {1433-7541},
year = {2015},
date = {2015-11-01},
urldate = {2015-11-01},
journal = {Pattern Analysis and Applications},
volume = {18},
number = {4},
pages = {933-943},
keywords = {Prometeo 2012, TIMuL},
pubstate = {published},
tppubtype = {article}
}
Valero-Mas, J. J.; Salamon, J.; Gómez, E.
Analyzing the influence of pitch quantization and note segmentation on singing voice alignment in the context of audio-based Query-by-Humming Proceedings Article
In: Proceedings of the 12th Sound and Music Computing Conference (SMC), pp. 371–378, Maynooth, Ireland, 2015, ISBN: 9--7809--92746629.
Abstract | Links | BibTeX | Tags: Prometeo 2012, TIMuL
@inproceedings{k331,
title = {Analyzing the influence of pitch quantization and note segmentation on singing voice alignment in the context of audio-based Query-by-Humming},
author = {J. J. Valero-Mas and J. Salamon and E. Gómez},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/331/QBH_SMC2015_CameraReady.pdf},
isbn = {9--7809--92746629},
year = {2015},
date = {2015-07-01},
booktitle = {Proceedings of the 12th Sound and Music Computing Conference (SMC)},
pages = {371--378},
address = {Maynooth, Ireland},
abstract = {Query-by-Humming (QBH) systems base their operation on aligning the melody sung/hummed by a user with a set of candidate melodies retrieved from music tunes. While MIDI-based QBH builds on the premise of existing annotated transcriptions for any candidate song, audio-based research makes use of melody extraction algorithms for the music tunes. In both cases, a melody abstraction process is required for solving issues commonly found in queries such as key transpositions or tempo deviations. Automatic music transcription is commonly used for this, but due to the reported limitations in state-of-the-art methods for real-world queries, other possibilities should be considered. In this work we explore three different melody representations, ranging from a general time-series one to more musical abstractions, which avoid the automatic transcription step, in the context of an audio-based QBH system. Results show that this abstraction process plays a key role in the overall accuracy of the system, obtaining the best scores when temporal segmentation is dynamically performed in terms of pitch change events in the melodic contour.},
keywords = {Prometeo 2012, TIMuL},
pubstate = {published},
tppubtype = {inproceedings}
}
Query-by-Humming (QBH) systems base their operation on aligning the melody sung/hummed by a user with a set of candidate melodies retrieved from music tunes. While MIDI-based QBH builds on the premise of existing annotated transcriptions for any candidate song, audio-based research makes use of melody extraction algorithms for the music tunes. In both cases, a melody abstraction process is required for solving issues commonly found in queries such as key transpositions or tempo deviations. Automatic music transcription is commonly used for this, but due to the reported limitations in state-of-the-art methods for real-world queries, other possibilities should be considered. In this work we explore three different melody representations, ranging from a general time-series one to more musical abstractions, which avoid the automatic transcription step, in the context of an audio-based QBH system. Results show that this abstraction process plays a key role in the overall accuracy of the system, obtaining the best scores when temporal segmentation is dynamically performed in terms of pitch change events in the melodic contour. Calvo-Zaragoza, J.; Oncina, J.
Clustering of Strokes from Pen-based Music Notation: An Experimental Study Proceedings Article
In: Paredes, Roberto; Cardoso, Jaime S.; Pardo, Xosé M. (Ed.): 7th Iberian Conference on Pattern Recognition and Image Analysis (IbPRIA), pp. 633-640, Springer, Santiago de Compostela, Spain, 2015, ISBN: 978-3-319-19389-2.
Links | BibTeX | Tags: Prometeo 2012, TIMuL
@inproceedings{k326,
title = {Clustering of Strokes from Pen-based Music Notation: An Experimental Study},
author = {J. Calvo-Zaragoza and J. Oncina},
editor = {Roberto Paredes and Jaime S. Cardoso and Xosé M. Pardo},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/326/clustering-strokes-pen.pdf},
isbn = {978-3-319-19389-2},
year = {2015},
date = {2015-06-01},
booktitle = {7th Iberian Conference on Pattern Recognition and Image Analysis (IbPRIA)},
pages = {633-640},
publisher = {Springer},
address = {Santiago de Compostela, Spain},
keywords = {Prometeo 2012, TIMuL},
pubstate = {published},
tppubtype = {inproceedings}
}
Micó, L.; Sanches, J.; Cardoso, J. S.
The vitality of pattern recognition and image analysis Journal Article
In: Neurocomputing, vol. 150, pp. 124-125, 2015, ISSN: 09252312.
BibTeX | Tags: Prometeo 2012, TIMuL
@article{k320,
title = {The vitality of pattern recognition and image analysis},
author = {L. Micó and J. Sanches and J. S. Cardoso},
issn = {09252312},
year = {2015},
date = {2015-01-01},
urldate = {2015-01-01},
journal = {Neurocomputing},
volume = {150},
pages = {124-125},
keywords = {Prometeo 2012, TIMuL},
pubstate = {published},
tppubtype = {article}
}
Rizo, D.; Iñesta, J. M.
A grammar for Plaine and Easie Code Proceedings Article
In: Roland, Perry; Kepper, Johannes (Ed.): Proceedings of the Music Encoding Initiative Conferences 2013 and 2014, pp. 54–64, 2015.
BibTeX | Tags: GRE-12-34, Prometeo 2012, TIMuL
@inproceedings{k321,
title = {A grammar for Plaine and Easie Code},
author = {D. Rizo and J. M. Iñesta},
editor = {Perry Roland and Johannes Kepper},
year = {2015},
date = {2015-01-01},
urldate = {2015-01-01},
booktitle = {Proceedings of the Music Encoding Initiative Conferences 2013 and 2014},
pages = {54--64},
keywords = {GRE-12-34, Prometeo 2012, TIMuL},
pubstate = {published},
tppubtype = {inproceedings}
}
Rico-Juan, J. R.; Calvo-Zaragoza, J.
Improving classification using a Confidence Matrix based on weak classifiers applied to OCR Journal Article
In: Neurocomputing, vol. 151, pp. 1354–1361, 2015, ISSN: 0925-2312.
Links | BibTeX | Tags: Prometeo 2012, TIMuL
@article{k323,
title = {Improving classification using a Confidence Matrix based on weak classifiers applied to OCR},
author = {J. R. Rico-Juan and J. Calvo-Zaragoza},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/323/cm.pdf},
issn = {0925-2312},
year = {2015},
date = {2015-01-01},
urldate = {2015-01-01},
journal = {Neurocomputing},
volume = {151},
pages = {1354–1361},
keywords = {Prometeo 2012, TIMuL},
pubstate = {published},
tppubtype = {article}
}
Calvo-Zaragoza, J.; Valero-Mas, J. J.; Rico-Juan, J. R
Improving kNN multi-label classification in Prototype Selection scenarios using class proposals Journal Article
In: Pattern Recognition, vol. 48, no. 5, pp. 1608-1622, 2015.
Links | BibTeX | Tags: Prometeo 2012, TIMuL
@article{k324,
title = {Improving kNN multi-label classification in Prototype Selection scenarios using class proposals},
author = {J. Calvo-Zaragoza and J. J. Valero-Mas and J. R Rico-Juan},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/324/improving-knn-multi.pdf},
year = {2015},
date = {2015-01-01},
urldate = {2015-01-01},
journal = {Pattern Recognition},
volume = {48},
number = {5},
pages = {1608-1622},
keywords = {Prometeo 2012, TIMuL},
pubstate = {published},
tppubtype = {article}
}
2014
Calvo-Zaragoza, J.; Oncina, J.
Recognition of Pen-Based Music Notation: the HOMUS dataset Proceedings Article
In: Proceedings of the 22nd International Conference on Pattern Recognition, pp. 3038-3043, Stockholm, Sweden, 2014, ISBN: 978-1-4799-5208-3.
Links | BibTeX | Tags: Prometeo 2012
@inproceedings{k316,
title = {Recognition of Pen-Based Music Notation: the HOMUS dataset},
author = {J. Calvo-Zaragoza and J. Oncina},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/316/homus.pdf},
isbn = {978-1-4799-5208-3},
year = {2014},
date = {2014-08-01},
urldate = {2014-08-01},
booktitle = {Proceedings of the 22nd International Conference on Pattern Recognition},
pages = {3038-3043},
address = {Stockholm, Sweden},
keywords = {Prometeo 2012},
pubstate = {published},
tppubtype = {inproceedings}
}
Higuera, C. De La; Oncina, J.
The most probable string: an algorithmic study Journal Article
In: Journal of Logic and Computation, vol. 24, no. 2, pp. 311-330, 2014, ISSN: 0955-792X.
Abstract | Links | BibTeX | Tags: Prometeo 2012, TIASA
@article{k304,
title = {The most probable string: an algorithmic study},
author = {C. De La Higuera and J. Oncina},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/304/J+Logic+Computation-2013.pdf},
issn = {0955-792X},
year = {2014},
date = {2014-01-01},
urldate = {2014-01-01},
journal = {Journal of Logic and Computation},
volume = {24},
number = {2},
pages = {311-330},
abstract = {The problem of finding the consensus (most probable string) for a distribution generated by a weighted finite automaton or a probabilistic grammar is related to a number of important questions: computing the distance between two distributions or finding the best translation (the most probable one) given a probabilistic finite state transducer. The problem is undecidable
with general weights and is NP-hard if the automaton is probabilistic. We give a pseudo-polynomial algorithm that solves a decision problem directly associated with the consensus string and answers if there is a (reasonably short) string whose probability is larger than a given bound in time polynomial in the the size of this bound, both for probabilistic finite automata
and probabilistic context-free grammars.We also study a randomized algorithm solving the same problem. Finally, we report links between the length of the consensus string and the probability of this string.},
keywords = {Prometeo 2012, TIASA},
pubstate = {published},
tppubtype = {article}
}
The problem of finding the consensus (most probable string) for a distribution generated by a weighted finite automaton or a probabilistic grammar is related to a number of important questions: computing the distance between two distributions or finding the best translation (the most probable one) given a probabilistic finite state transducer. The problem is undecidable
with general weights and is NP-hard if the automaton is probabilistic. We give a pseudo-polynomial algorithm that solves a decision problem directly associated with the consensus string and answers if there is a (reasonably short) string whose probability is larger than a given bound in time polynomial in the the size of this bound, both for probabilistic finite automata
and probabilistic context-free grammars.We also study a randomized algorithm solving the same problem. Finally, we report links between the length of the consensus string and the probability of this string. Micó, L.; Oncina, J.
Dynamic Insertions in TLAESA fast NN Search Algorithm Proceedings Article
In: Proceedings of the 22nd International Conference on Pattern Recognition, ICPR, Stockholm, Sweden, 2014, ISBN: 978-1-4799-5208-3.
Abstract | Links | BibTeX | Tags: Prometeo 2012, TIMuL
@inproceedings{k319,
title = {Dynamic Insertions in TLAESA fast NN Search Algorithm},
author = {L. Micó and J. Oncina},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/319/icpr-2014.pdf},
isbn = {978-1-4799-5208-3},
year = {2014},
date = {2014-01-01},
booktitle = {Proceedings of the 22nd International Conference on Pattern Recognition, ICPR},
address = {Stockholm, Sweden},
abstract = {Nearest Neighbour search (NNS) is a widely used
technique in Pattern Recognition. In order to speed up the search many indexing techniques have been proposed. The need to work with large dynamic databases in interactive or online systems, has resulted in an increase interest in adapting or
creating fast methods to update these indexes. TLAESA is a fast search algorithm that computes a very low number of distance computations with sublinear overhead using a branch and bound technique.
In this paper, we propose a new fast updating method for the
TLAESA index. The behaviour of this index has been analysed
theoretical and experimentally. We have obtained a log-square
upper bound of the rebuilding expected time. This bound has
been verified experimentally on several synthetic and real data
experiments.},
keywords = {Prometeo 2012, TIMuL},
pubstate = {published},
tppubtype = {inproceedings}
}
Nearest Neighbour search (NNS) is a widely used
technique in Pattern Recognition. In order to speed up the search many indexing techniques have been proposed. The need to work with large dynamic databases in interactive or online systems, has resulted in an increase interest in adapting or
creating fast methods to update these indexes. TLAESA is a fast search algorithm that computes a very low number of distance computations with sublinear overhead using a branch and bound technique.
In this paper, we propose a new fast updating method for the
TLAESA index. The behaviour of this index has been analysed
theoretical and experimentally. We have obtained a log-square
upper bound of the rebuilding expected time. This bound has
been verified experimentally on several synthetic and real data
experiments.2013
Calvo-Zaragoza, J.; Oncina, J.
Human-Computer Interaction for Optical Music Recognition tasks Proceedings Article
In: Actas del III Workshop de Reconocimiento de Formas y Análisis de Imágenes, pp. 9-12, Madrid, Spain, 2013, ISBN: 978-84-695-8332-6.
Links | BibTeX | Tags: Prometeo 2012, TIASA
@inproceedings{k306,
title = {Human-Computer Interaction for Optical Music Recognition tasks},
author = {J. Calvo-Zaragoza and J. Oncina},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/306/wsrfai2013_submission_3.pdf},
isbn = {978-84-695-8332-6},
year = {2013},
date = {2013-09-01},
urldate = {2013-09-01},
booktitle = {Actas del III Workshop de Reconocimiento de Formas y Análisis de Imágenes},
pages = {9-12},
address = {Madrid, Spain},
keywords = {Prometeo 2012, TIASA},
pubstate = {published},
tppubtype = {inproceedings}
}
Higuera, C. De La; Oncina, J.
Computing the Most Probable String with a Probabilistic Finite State Machine Proceedings Article
In: Nederhof, Mark-Jan (Ed.): Proceedings of the 11th International Conference on Finite State Methods and Natural Language Processing, pp. 1-8, Association for Computational Linguistics, 2013.
Abstract | Links | BibTeX | Tags: Prometeo 2012
@inproceedings{k314,
title = {Computing the Most Probable String with a Probabilistic Finite State Machine},
author = {C. De La Higuera and J. Oncina},
editor = {Mark-Jan Nederhof},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/314/W13-1801.pdf},
year = {2013},
date = {2013-07-01},
urldate = {2013-07-01},
booktitle = {Proceedings of the 11th International Conference on Finite State Methods and Natural Language Processing},
pages = {1-8},
publisher = {Association for Computational Linguistics},
abstract = {The problem of finding the consensus / most
probable string for a distribution generated by
a probabilistic finite automaton or a hidden
Markov model arises in a number of natural
language processing tasks: it has to be solved
in several transducer related tasks like opti-
mal decoding in speech, or finding the most
probable translation of an input sentence. We
provide an algorithm which solves these prob-
lems in time polynomial in the inverse of the
probability of the most probable string, which
in practise makes the computation tractable in
many cases. We also show that this exact com-
putation compares favourably with the tradi-
tional Viterbi computation.},
keywords = {Prometeo 2012},
pubstate = {published},
tppubtype = {inproceedings}
}
The problem of finding the consensus / most
probable string for a distribution generated by
a probabilistic finite automaton or a hidden
Markov model arises in a number of natural
language processing tasks: it has to be solved
in several transducer related tasks like opti-
mal decoding in speech, or finding the most
probable translation of an input sentence. We
provide an algorithm which solves these prob-
lems in time polynomial in the inverse of the
probability of the most probable string, which
in practise makes the computation tractable in
many cases. We also show that this exact com-
putation compares favourably with the tradi-
tional Viterbi computation. Hontanilla, M.; Pérez-Sancho, C.; Iñesta, J. M.
Modeling Musical Style with Language Models for Composer Recognition Journal Article
In: Lecture Notes in Computer Science, vol. 7887, pp. 740-748, 2013, ISSN: 0302-9743.
Abstract | Links | BibTeX | Tags: DRIMS, Prometeo 2012
@article{k300,
title = {Modeling Musical Style with Language Models for Composer Recognition},
author = {M. Hontanilla and C. Pérez-Sancho and J. M. Iñesta},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/300/10.1007_978-3-642-38628-2_88.pdf},
issn = {0302-9743},
year = {2013},
date = {2013-06-01},
journal = {Lecture Notes in Computer Science},
volume = {7887},
pages = {740-748},
abstract = {In this paper we present an application of language modeling using n-grams to model the style of different composers. For this, we repeated the experiments performed in previous works by other authors using a corpus of 5 composers from the Baroque and Classical periods. In these experiments we found some signs that the results could be influenced by external factors other than the composers’ styles, such as the heterogeneity in the musical forms selected for the corpus. In order to as- sess the validity of the modeling techniques to capture the own personal style of the composers, a new experiment was performed with a corpus of fugues from Bach and Shostakovich. All these experiments show that language modeling is a suitable tool for modeling musical style, even when the styles of the different datasets are affected by several factors.},
keywords = {DRIMS, Prometeo 2012},
pubstate = {published},
tppubtype = {article}
}
In this paper we present an application of language modeling using n-grams to model the style of different composers. For this, we repeated the experiments performed in previous works by other authors using a corpus of 5 composers from the Baroque and Classical periods. In these experiments we found some signs that the results could be influenced by external factors other than the composers’ styles, such as the heterogeneity in the musical forms selected for the corpus. In order to as- sess the validity of the modeling techniques to capture the own personal style of the composers, a new experiment was performed with a corpus of fugues from Bach and Shostakovich. All these experiments show that language modeling is a suitable tool for modeling musical style, even when the styles of the different datasets are affected by several factors. Serrano, A.; Micó, L.; Oncina, J.
Which fast nearest neighbour search algorithm to use? Journal Article
In: Lecture Notes in Computer Science, vol. 7887, pp. 567-574, 2013.
Links | BibTeX | Tags: Prometeo 2012, TIASA
@article{k301,
title = {Which fast nearest neighbour search algorithm to use?},
author = {A. Serrano and L. Micó and J. Oncina},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/301/IbPria13.pdf},
year = {2013},
date = {2013-06-01},
journal = {Lecture Notes in Computer Science},
volume = {7887},
pages = {567-574},
keywords = {Prometeo 2012, TIASA},
pubstate = {published},
tppubtype = {article}
}
Iñesta, J. M.; Pérez-Sancho, C.
Interactive multimodal music transcription Proceedings Article
In: Proc. of IEEE Int. Conf. on Acoustics, Speech and Signal Processing (ICASSP 2013), pp. 211-215, IEEE, Vancouver, Canada, 2013, ISBN: 978-1-4799-0356-6.
Abstract | BibTeX | Tags: DRIMS, Prometeo 2012
@inproceedings{k299,
title = {Interactive multimodal music transcription},
author = {J. M. Iñesta and C. Pérez-Sancho},
isbn = {978-1-4799-0356-6},
year = {2013},
date = {2013-05-01},
booktitle = {Proc. of IEEE Int. Conf. on Acoustics, Speech and Signal Processing (ICASSP 2013)},
pages = {211-215},
publisher = {IEEE},
address = {Vancouver, Canada},
abstract = {Automatic music transcription has usually been performed as an autonomous task and its evaluation has been made in terms of precision, recall, accuracy, etc. Nevertheless, in this work, assuming that the state of the art is far from being perfect, it is considered as an interactive one, where an expert user is assisted in its work by a transcription tool. In this context, the performance evaluation of the system turns into an assessment of how many user interactions are needed to complete the work. The strategy is that the user interactions can be used by the system to improve its performance in an adaptive way, thus minimizing the workload. Also, a multimodal approach has been implemented, in such a way that different sources of information, like onsets, beats, and meter, are used to detect notes in a musical audio excerpt. The system is focused on monotimbral polyphonic transcription.},
keywords = {DRIMS, Prometeo 2012},
pubstate = {published},
tppubtype = {inproceedings}
}
Automatic music transcription has usually been performed as an autonomous task and its evaluation has been made in terms of precision, recall, accuracy, etc. Nevertheless, in this work, assuming that the state of the art is far from being perfect, it is considered as an interactive one, where an expert user is assisted in its work by a transcription tool. In this context, the performance evaluation of the system turns into an assessment of how many user interactions are needed to complete the work. The strategy is that the user interactions can be used by the system to improve its performance in an adaptive way, thus minimizing the workload. Also, a multimodal approach has been implemented, in such a way that different sources of information, like onsets, beats, and meter, are used to detect notes in a musical audio excerpt. The system is focused on monotimbral polyphonic transcription. Sanches, J. M.; Micó, L.; Cardoso, J. S.
Pattern Recognition and Image Analysis 6th Iberian Conference, IbPRIA 2013 Book
Springer, 2013.
BibTeX | Tags: Prometeo 2012, TIASA
@book{k302,
title = {Pattern Recognition and Image Analysis 6th Iberian Conference, IbPRIA 2013},
author = {J. M. Sanches and L. Micó and J. S. Cardoso},
editor = {J. M. Sanches and L. Micó and J. S. Cardoso},
year = {2013},
date = {2013-01-01},
publisher = {Springer},
keywords = {Prometeo 2012, TIASA},
pubstate = {published},
tppubtype = {book}
}
Calvo-Zaragoza, J.; Oncina, J.; Iñesta, J. M.
Recognition of Online Handwritten Music Symbols Proceedings Article
In: Proceedings of the 6th International Workshop on Machine Learning and Music, Prague, Czech Republic, 2013.
Abstract | Links | BibTeX | Tags: Prometeo 2012, TIASA
@inproceedings{k307,
title = {Recognition of Online Handwritten Music Symbols},
author = {J. Calvo-Zaragoza and J. Oncina and J. M. Iñesta},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/307/calvozaragoza-mml13.pdf},
year = {2013},
date = {2013-01-01},
urldate = {2013-01-01},
booktitle = {Proceedings of the 6th International Workshop on Machine Learning and Music},
address = {Prague, Czech Republic},
abstract = {An effective way of digitizing a new musical composition is to use an e-pen and tablet application in which the user's pen strokes are recognized online and the digital score is created with the sole effort of the composition itself. This work aims to be a starting point for research on the recognition of online handwritten music notation. To this end, different alternatives within the two modalities of recognition resulting from this data are presented: online recognition, which uses the strokes marked by a pen, and offline recognition, which uses the image generated after drawing the symbol. A comparative experiment with common machine learning algorithms over a dataset of 3800 samples and 32 different music symbols is presented. Results show that samples of the actual user are needed if good classification rates are pursued. Moreover, algorithms using the online data, on average, achieve better classifocation results than the others.},
keywords = {Prometeo 2012, TIASA},
pubstate = {published},
tppubtype = {inproceedings}
}
An effective way of digitizing a new musical composition is to use an e-pen and tablet application in which the user's pen strokes are recognized online and the digital score is created with the sole effort of the composition itself. This work aims to be a starting point for research on the recognition of online handwritten music notation. To this end, different alternatives within the two modalities of recognition resulting from this data are presented: online recognition, which uses the strokes marked by a pen, and offline recognition, which uses the image generated after drawing the symbol. A comparative experiment with common machine learning algorithms over a dataset of 3800 samples and 32 different music symbols is presented. Results show that samples of the actual user are needed if good classification rates are pursued. Moreover, algorithms using the online data, on average, achieve better classifocation results than the others.2012
López, D.; Calera-Rubio, J.; Gallego-Sánchez, A. J.
Inference of k-Testable Directed Acyclic Graph Languages Proceedings Article
In: Journal of Machine Learning Research: Workshop and Conference Proceedings, Vol. 21: ICGI 2012, pp. 149-163, 2012.
Abstract | Links | BibTeX | Tags: PASCAL2, Prometeo 2012, TIASA
@inproceedings{k296,
title = {Inference of k-Testable Directed Acyclic Graph Languages},
author = {D. López and J. Calera-Rubio and A. J. Gallego-Sánchez},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/296/lopez12a.pdf},
year = {2012},
date = {2012-01-01},
booktitle = {Journal of Machine Learning Research: Workshop and Conference Proceedings, Vol. 21: ICGI 2012},
pages = {149-163},
abstract = {In this paper, we tackle the task of graph language learning. We first extend the well-known classes of k-testability and k-testability in the strict sense languages to directed graph languages. Second, we propose a graph automata model for directed acyclic graph languages. This graph automata model is used to 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.},
keywords = {PASCAL2, Prometeo 2012, TIASA},
pubstate = {published},
tppubtype = {inproceedings}
}
In this paper, we tackle the task of graph language learning. We first extend the well-known classes of k-testability and k-testability in the strict sense languages to directed graph languages. Second, we propose a graph automata model for directed acyclic graph languages. This graph automata model is used to 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.
2016
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.
2015
Calvo-Zaragoza, J.; Barbancho, I.; Tardón, L. J.; Barbancho, A. M.
Avoiding staff removal stage in optical music recognition: application to scores written in white mensural notation Journal Article
In: Pattern Analysis and Applications, vol. 18, no. 4, pp. 933-943, 2015, ISSN: 1433-7541.
Links | BibTeX | Tags: Prometeo 2012, TIMuL
@article{k318,
title = {Avoiding staff removal stage in optical music recognition: application to scores written in white mensural notation},
author = {J. Calvo-Zaragoza and I. Barbancho and L. J. Tardón and A. M. Barbancho},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/318/paaa-jcalvo.pdf},
issn = {1433-7541},
year = {2015},
date = {2015-11-01},
urldate = {2015-11-01},
journal = {Pattern Analysis and Applications},
volume = {18},
number = {4},
pages = {933-943},
keywords = {Prometeo 2012, TIMuL},
pubstate = {published},
tppubtype = {article}
}
Valero-Mas, J. J.; Salamon, J.; Gómez, E.
Analyzing the influence of pitch quantization and note segmentation on singing voice alignment in the context of audio-based Query-by-Humming Proceedings Article
In: Proceedings of the 12th Sound and Music Computing Conference (SMC), pp. 371–378, Maynooth, Ireland, 2015, ISBN: 9--7809--92746629.
Abstract | Links | BibTeX | Tags: Prometeo 2012, TIMuL
@inproceedings{k331,
title = {Analyzing the influence of pitch quantization and note segmentation on singing voice alignment in the context of audio-based Query-by-Humming},
author = {J. J. Valero-Mas and J. Salamon and E. Gómez},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/331/QBH_SMC2015_CameraReady.pdf},
isbn = {9--7809--92746629},
year = {2015},
date = {2015-07-01},
booktitle = {Proceedings of the 12th Sound and Music Computing Conference (SMC)},
pages = {371--378},
address = {Maynooth, Ireland},
abstract = {Query-by-Humming (QBH) systems base their operation on aligning the melody sung/hummed by a user with a set of candidate melodies retrieved from music tunes. While MIDI-based QBH builds on the premise of existing annotated transcriptions for any candidate song, audio-based research makes use of melody extraction algorithms for the music tunes. In both cases, a melody abstraction process is required for solving issues commonly found in queries such as key transpositions or tempo deviations. Automatic music transcription is commonly used for this, but due to the reported limitations in state-of-the-art methods for real-world queries, other possibilities should be considered. In this work we explore three different melody representations, ranging from a general time-series one to more musical abstractions, which avoid the automatic transcription step, in the context of an audio-based QBH system. Results show that this abstraction process plays a key role in the overall accuracy of the system, obtaining the best scores when temporal segmentation is dynamically performed in terms of pitch change events in the melodic contour.},
keywords = {Prometeo 2012, TIMuL},
pubstate = {published},
tppubtype = {inproceedings}
}
Query-by-Humming (QBH) systems base their operation on aligning the melody sung/hummed by a user with a set of candidate melodies retrieved from music tunes. While MIDI-based QBH builds on the premise of existing annotated transcriptions for any candidate song, audio-based research makes use of melody extraction algorithms for the music tunes. In both cases, a melody abstraction process is required for solving issues commonly found in queries such as key transpositions or tempo deviations. Automatic music transcription is commonly used for this, but due to the reported limitations in state-of-the-art methods for real-world queries, other possibilities should be considered. In this work we explore three different melody representations, ranging from a general time-series one to more musical abstractions, which avoid the automatic transcription step, in the context of an audio-based QBH system. Results show that this abstraction process plays a key role in the overall accuracy of the system, obtaining the best scores when temporal segmentation is dynamically performed in terms of pitch change events in the melodic contour.
Calvo-Zaragoza, J.; Oncina, J.
Clustering of Strokes from Pen-based Music Notation: An Experimental Study Proceedings Article
In: Paredes, Roberto; Cardoso, Jaime S.; Pardo, Xosé M. (Ed.): 7th Iberian Conference on Pattern Recognition and Image Analysis (IbPRIA), pp. 633-640, Springer, Santiago de Compostela, Spain, 2015, ISBN: 978-3-319-19389-2.
Links | BibTeX | Tags: Prometeo 2012, TIMuL
@inproceedings{k326,
title = {Clustering of Strokes from Pen-based Music Notation: An Experimental Study},
author = {J. Calvo-Zaragoza and J. Oncina},
editor = {Roberto Paredes and Jaime S. Cardoso and Xosé M. Pardo},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/326/clustering-strokes-pen.pdf},
isbn = {978-3-319-19389-2},
year = {2015},
date = {2015-06-01},
booktitle = {7th Iberian Conference on Pattern Recognition and Image Analysis (IbPRIA)},
pages = {633-640},
publisher = {Springer},
address = {Santiago de Compostela, Spain},
keywords = {Prometeo 2012, TIMuL},
pubstate = {published},
tppubtype = {inproceedings}
}
Micó, L.; Sanches, J.; Cardoso, J. S.
The vitality of pattern recognition and image analysis Journal Article
In: Neurocomputing, vol. 150, pp. 124-125, 2015, ISSN: 09252312.
BibTeX | Tags: Prometeo 2012, TIMuL
@article{k320,
title = {The vitality of pattern recognition and image analysis},
author = {L. Micó and J. Sanches and J. S. Cardoso},
issn = {09252312},
year = {2015},
date = {2015-01-01},
urldate = {2015-01-01},
journal = {Neurocomputing},
volume = {150},
pages = {124-125},
keywords = {Prometeo 2012, TIMuL},
pubstate = {published},
tppubtype = {article}
}
Rizo, D.; Iñesta, J. M.
A grammar for Plaine and Easie Code Proceedings Article
In: Roland, Perry; Kepper, Johannes (Ed.): Proceedings of the Music Encoding Initiative Conferences 2013 and 2014, pp. 54–64, 2015.
BibTeX | Tags: GRE-12-34, Prometeo 2012, TIMuL
@inproceedings{k321,
title = {A grammar for Plaine and Easie Code},
author = {D. Rizo and J. M. Iñesta},
editor = {Perry Roland and Johannes Kepper},
year = {2015},
date = {2015-01-01},
urldate = {2015-01-01},
booktitle = {Proceedings of the Music Encoding Initiative Conferences 2013 and 2014},
pages = {54--64},
keywords = {GRE-12-34, Prometeo 2012, TIMuL},
pubstate = {published},
tppubtype = {inproceedings}
}
Rico-Juan, J. R.; Calvo-Zaragoza, J.
Improving classification using a Confidence Matrix based on weak classifiers applied to OCR Journal Article
In: Neurocomputing, vol. 151, pp. 1354–1361, 2015, ISSN: 0925-2312.
Links | BibTeX | Tags: Prometeo 2012, TIMuL
@article{k323,
title = {Improving classification using a Confidence Matrix based on weak classifiers applied to OCR},
author = {J. R. Rico-Juan and J. Calvo-Zaragoza},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/323/cm.pdf},
issn = {0925-2312},
year = {2015},
date = {2015-01-01},
urldate = {2015-01-01},
journal = {Neurocomputing},
volume = {151},
pages = {1354–1361},
keywords = {Prometeo 2012, TIMuL},
pubstate = {published},
tppubtype = {article}
}
Calvo-Zaragoza, J.; Valero-Mas, J. J.; Rico-Juan, J. R
Improving kNN multi-label classification in Prototype Selection scenarios using class proposals Journal Article
In: Pattern Recognition, vol. 48, no. 5, pp. 1608-1622, 2015.
Links | BibTeX | Tags: Prometeo 2012, TIMuL
@article{k324,
title = {Improving kNN multi-label classification in Prototype Selection scenarios using class proposals},
author = {J. Calvo-Zaragoza and J. J. Valero-Mas and J. R Rico-Juan},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/324/improving-knn-multi.pdf},
year = {2015},
date = {2015-01-01},
urldate = {2015-01-01},
journal = {Pattern Recognition},
volume = {48},
number = {5},
pages = {1608-1622},
keywords = {Prometeo 2012, TIMuL},
pubstate = {published},
tppubtype = {article}
}
2014
Calvo-Zaragoza, J.; Oncina, J.
Recognition of Pen-Based Music Notation: the HOMUS dataset Proceedings Article
In: Proceedings of the 22nd International Conference on Pattern Recognition, pp. 3038-3043, Stockholm, Sweden, 2014, ISBN: 978-1-4799-5208-3.
Links | BibTeX | Tags: Prometeo 2012
@inproceedings{k316,
title = {Recognition of Pen-Based Music Notation: the HOMUS dataset},
author = {J. Calvo-Zaragoza and J. Oncina},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/316/homus.pdf},
isbn = {978-1-4799-5208-3},
year = {2014},
date = {2014-08-01},
urldate = {2014-08-01},
booktitle = {Proceedings of the 22nd International Conference on Pattern Recognition},
pages = {3038-3043},
address = {Stockholm, Sweden},
keywords = {Prometeo 2012},
pubstate = {published},
tppubtype = {inproceedings}
}
Higuera, C. De La; Oncina, J.
The most probable string: an algorithmic study Journal Article
In: Journal of Logic and Computation, vol. 24, no. 2, pp. 311-330, 2014, ISSN: 0955-792X.
Abstract | Links | BibTeX | Tags: Prometeo 2012, TIASA
@article{k304,
title = {The most probable string: an algorithmic study},
author = {C. De La Higuera and J. Oncina},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/304/J+Logic+Computation-2013.pdf},
issn = {0955-792X},
year = {2014},
date = {2014-01-01},
urldate = {2014-01-01},
journal = {Journal of Logic and Computation},
volume = {24},
number = {2},
pages = {311-330},
abstract = {The problem of finding the consensus (most probable string) for a distribution generated by a weighted finite automaton or a probabilistic grammar is related to a number of important questions: computing the distance between two distributions or finding the best translation (the most probable one) given a probabilistic finite state transducer. The problem is undecidable
with general weights and is NP-hard if the automaton is probabilistic. We give a pseudo-polynomial algorithm that solves a decision problem directly associated with the consensus string and answers if there is a (reasonably short) string whose probability is larger than a given bound in time polynomial in the the size of this bound, both for probabilistic finite automata
and probabilistic context-free grammars.We also study a randomized algorithm solving the same problem. Finally, we report links between the length of the consensus string and the probability of this string.},
keywords = {Prometeo 2012, TIASA},
pubstate = {published},
tppubtype = {article}
}
The problem of finding the consensus (most probable string) for a distribution generated by a weighted finite automaton or a probabilistic grammar is related to a number of important questions: computing the distance between two distributions or finding the best translation (the most probable one) given a probabilistic finite state transducer. The problem is undecidable
with general weights and is NP-hard if the automaton is probabilistic. We give a pseudo-polynomial algorithm that solves a decision problem directly associated with the consensus string and answers if there is a (reasonably short) string whose probability is larger than a given bound in time polynomial in the the size of this bound, both for probabilistic finite automata
and probabilistic context-free grammars.We also study a randomized algorithm solving the same problem. Finally, we report links between the length of the consensus string and the probability of this string.
with general weights and is NP-hard if the automaton is probabilistic. We give a pseudo-polynomial algorithm that solves a decision problem directly associated with the consensus string and answers if there is a (reasonably short) string whose probability is larger than a given bound in time polynomial in the the size of this bound, both for probabilistic finite automata
and probabilistic context-free grammars.We also study a randomized algorithm solving the same problem. Finally, we report links between the length of the consensus string and the probability of this string.
Micó, L.; Oncina, J.
Dynamic Insertions in TLAESA fast NN Search Algorithm Proceedings Article
In: Proceedings of the 22nd International Conference on Pattern Recognition, ICPR, Stockholm, Sweden, 2014, ISBN: 978-1-4799-5208-3.
Abstract | Links | BibTeX | Tags: Prometeo 2012, TIMuL
@inproceedings{k319,
title = {Dynamic Insertions in TLAESA fast NN Search Algorithm},
author = {L. Micó and J. Oncina},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/319/icpr-2014.pdf},
isbn = {978-1-4799-5208-3},
year = {2014},
date = {2014-01-01},
booktitle = {Proceedings of the 22nd International Conference on Pattern Recognition, ICPR},
address = {Stockholm, Sweden},
abstract = {Nearest Neighbour search (NNS) is a widely used
technique in Pattern Recognition. In order to speed up the search many indexing techniques have been proposed. The need to work with large dynamic databases in interactive or online systems, has resulted in an increase interest in adapting or
creating fast methods to update these indexes. TLAESA is a fast search algorithm that computes a very low number of distance computations with sublinear overhead using a branch and bound technique.
In this paper, we propose a new fast updating method for the
TLAESA index. The behaviour of this index has been analysed
theoretical and experimentally. We have obtained a log-square
upper bound of the rebuilding expected time. This bound has
been verified experimentally on several synthetic and real data
experiments.},
keywords = {Prometeo 2012, TIMuL},
pubstate = {published},
tppubtype = {inproceedings}
}
Nearest Neighbour search (NNS) is a widely used
technique in Pattern Recognition. In order to speed up the search many indexing techniques have been proposed. The need to work with large dynamic databases in interactive or online systems, has resulted in an increase interest in adapting or
creating fast methods to update these indexes. TLAESA is a fast search algorithm that computes a very low number of distance computations with sublinear overhead using a branch and bound technique.
In this paper, we propose a new fast updating method for the
TLAESA index. The behaviour of this index has been analysed
theoretical and experimentally. We have obtained a log-square
upper bound of the rebuilding expected time. This bound has
been verified experimentally on several synthetic and real data
experiments.
technique in Pattern Recognition. In order to speed up the search many indexing techniques have been proposed. The need to work with large dynamic databases in interactive or online systems, has resulted in an increase interest in adapting or
creating fast methods to update these indexes. TLAESA is a fast search algorithm that computes a very low number of distance computations with sublinear overhead using a branch and bound technique.
In this paper, we propose a new fast updating method for the
TLAESA index. The behaviour of this index has been analysed
theoretical and experimentally. We have obtained a log-square
upper bound of the rebuilding expected time. This bound has
been verified experimentally on several synthetic and real data
experiments.
2013
Calvo-Zaragoza, J.; Oncina, J.
Human-Computer Interaction for Optical Music Recognition tasks Proceedings Article
In: Actas del III Workshop de Reconocimiento de Formas y Análisis de Imágenes, pp. 9-12, Madrid, Spain, 2013, ISBN: 978-84-695-8332-6.
Links | BibTeX | Tags: Prometeo 2012, TIASA
@inproceedings{k306,
title = {Human-Computer Interaction for Optical Music Recognition tasks},
author = {J. Calvo-Zaragoza and J. Oncina},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/306/wsrfai2013_submission_3.pdf},
isbn = {978-84-695-8332-6},
year = {2013},
date = {2013-09-01},
urldate = {2013-09-01},
booktitle = {Actas del III Workshop de Reconocimiento de Formas y Análisis de Imágenes},
pages = {9-12},
address = {Madrid, Spain},
keywords = {Prometeo 2012, TIASA},
pubstate = {published},
tppubtype = {inproceedings}
}
Higuera, C. De La; Oncina, J.
Computing the Most Probable String with a Probabilistic Finite State Machine Proceedings Article
In: Nederhof, Mark-Jan (Ed.): Proceedings of the 11th International Conference on Finite State Methods and Natural Language Processing, pp. 1-8, Association for Computational Linguistics, 2013.
Abstract | Links | BibTeX | Tags: Prometeo 2012
@inproceedings{k314,
title = {Computing the Most Probable String with a Probabilistic Finite State Machine},
author = {C. De La Higuera and J. Oncina},
editor = {Mark-Jan Nederhof},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/314/W13-1801.pdf},
year = {2013},
date = {2013-07-01},
urldate = {2013-07-01},
booktitle = {Proceedings of the 11th International Conference on Finite State Methods and Natural Language Processing},
pages = {1-8},
publisher = {Association for Computational Linguistics},
abstract = {The problem of finding the consensus / most
probable string for a distribution generated by
a probabilistic finite automaton or a hidden
Markov model arises in a number of natural
language processing tasks: it has to be solved
in several transducer related tasks like opti-
mal decoding in speech, or finding the most
probable translation of an input sentence. We
provide an algorithm which solves these prob-
lems in time polynomial in the inverse of the
probability of the most probable string, which
in practise makes the computation tractable in
many cases. We also show that this exact com-
putation compares favourably with the tradi-
tional Viterbi computation.},
keywords = {Prometeo 2012},
pubstate = {published},
tppubtype = {inproceedings}
}
The problem of finding the consensus / most
probable string for a distribution generated by
a probabilistic finite automaton or a hidden
Markov model arises in a number of natural
language processing tasks: it has to be solved
in several transducer related tasks like opti-
mal decoding in speech, or finding the most
probable translation of an input sentence. We
provide an algorithm which solves these prob-
lems in time polynomial in the inverse of the
probability of the most probable string, which
in practise makes the computation tractable in
many cases. We also show that this exact com-
putation compares favourably with the tradi-
tional Viterbi computation.
probable string for a distribution generated by
a probabilistic finite automaton or a hidden
Markov model arises in a number of natural
language processing tasks: it has to be solved
in several transducer related tasks like opti-
mal decoding in speech, or finding the most
probable translation of an input sentence. We
provide an algorithm which solves these prob-
lems in time polynomial in the inverse of the
probability of the most probable string, which
in practise makes the computation tractable in
many cases. We also show that this exact com-
putation compares favourably with the tradi-
tional Viterbi computation.
Hontanilla, M.; Pérez-Sancho, C.; Iñesta, J. M.
Modeling Musical Style with Language Models for Composer Recognition Journal Article
In: Lecture Notes in Computer Science, vol. 7887, pp. 740-748, 2013, ISSN: 0302-9743.
Abstract | Links | BibTeX | Tags: DRIMS, Prometeo 2012
@article{k300,
title = {Modeling Musical Style with Language Models for Composer Recognition},
author = {M. Hontanilla and C. Pérez-Sancho and J. M. Iñesta},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/300/10.1007_978-3-642-38628-2_88.pdf},
issn = {0302-9743},
year = {2013},
date = {2013-06-01},
journal = {Lecture Notes in Computer Science},
volume = {7887},
pages = {740-748},
abstract = {In this paper we present an application of language modeling using n-grams to model the style of different composers. For this, we repeated the experiments performed in previous works by other authors using a corpus of 5 composers from the Baroque and Classical periods. In these experiments we found some signs that the results could be influenced by external factors other than the composers’ styles, such as the heterogeneity in the musical forms selected for the corpus. In order to as- sess the validity of the modeling techniques to capture the own personal style of the composers, a new experiment was performed with a corpus of fugues from Bach and Shostakovich. All these experiments show that language modeling is a suitable tool for modeling musical style, even when the styles of the different datasets are affected by several factors.},
keywords = {DRIMS, Prometeo 2012},
pubstate = {published},
tppubtype = {article}
}
In this paper we present an application of language modeling using n-grams to model the style of different composers. For this, we repeated the experiments performed in previous works by other authors using a corpus of 5 composers from the Baroque and Classical periods. In these experiments we found some signs that the results could be influenced by external factors other than the composers’ styles, such as the heterogeneity in the musical forms selected for the corpus. In order to as- sess the validity of the modeling techniques to capture the own personal style of the composers, a new experiment was performed with a corpus of fugues from Bach and Shostakovich. All these experiments show that language modeling is a suitable tool for modeling musical style, even when the styles of the different datasets are affected by several factors.
Serrano, A.; Micó, L.; Oncina, J.
Which fast nearest neighbour search algorithm to use? Journal Article
In: Lecture Notes in Computer Science, vol. 7887, pp. 567-574, 2013.
Links | BibTeX | Tags: Prometeo 2012, TIASA
@article{k301,
title = {Which fast nearest neighbour search algorithm to use?},
author = {A. Serrano and L. Micó and J. Oncina},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/301/IbPria13.pdf},
year = {2013},
date = {2013-06-01},
journal = {Lecture Notes in Computer Science},
volume = {7887},
pages = {567-574},
keywords = {Prometeo 2012, TIASA},
pubstate = {published},
tppubtype = {article}
}
Iñesta, J. M.; Pérez-Sancho, C.
Interactive multimodal music transcription Proceedings Article
In: Proc. of IEEE Int. Conf. on Acoustics, Speech and Signal Processing (ICASSP 2013), pp. 211-215, IEEE, Vancouver, Canada, 2013, ISBN: 978-1-4799-0356-6.
Abstract | BibTeX | Tags: DRIMS, Prometeo 2012
@inproceedings{k299,
title = {Interactive multimodal music transcription},
author = {J. M. Iñesta and C. Pérez-Sancho},
isbn = {978-1-4799-0356-6},
year = {2013},
date = {2013-05-01},
booktitle = {Proc. of IEEE Int. Conf. on Acoustics, Speech and Signal Processing (ICASSP 2013)},
pages = {211-215},
publisher = {IEEE},
address = {Vancouver, Canada},
abstract = {Automatic music transcription has usually been performed as an autonomous task and its evaluation has been made in terms of precision, recall, accuracy, etc. Nevertheless, in this work, assuming that the state of the art is far from being perfect, it is considered as an interactive one, where an expert user is assisted in its work by a transcription tool. In this context, the performance evaluation of the system turns into an assessment of how many user interactions are needed to complete the work. The strategy is that the user interactions can be used by the system to improve its performance in an adaptive way, thus minimizing the workload. Also, a multimodal approach has been implemented, in such a way that different sources of information, like onsets, beats, and meter, are used to detect notes in a musical audio excerpt. The system is focused on monotimbral polyphonic transcription.},
keywords = {DRIMS, Prometeo 2012},
pubstate = {published},
tppubtype = {inproceedings}
}
Automatic music transcription has usually been performed as an autonomous task and its evaluation has been made in terms of precision, recall, accuracy, etc. Nevertheless, in this work, assuming that the state of the art is far from being perfect, it is considered as an interactive one, where an expert user is assisted in its work by a transcription tool. In this context, the performance evaluation of the system turns into an assessment of how many user interactions are needed to complete the work. The strategy is that the user interactions can be used by the system to improve its performance in an adaptive way, thus minimizing the workload. Also, a multimodal approach has been implemented, in such a way that different sources of information, like onsets, beats, and meter, are used to detect notes in a musical audio excerpt. The system is focused on monotimbral polyphonic transcription.
Sanches, J. M.; Micó, L.; Cardoso, J. S.
Pattern Recognition and Image Analysis 6th Iberian Conference, IbPRIA 2013 Book
Springer, 2013.
BibTeX | Tags: Prometeo 2012, TIASA
@book{k302,
title = {Pattern Recognition and Image Analysis 6th Iberian Conference, IbPRIA 2013},
author = {J. M. Sanches and L. Micó and J. S. Cardoso},
editor = {J. M. Sanches and L. Micó and J. S. Cardoso},
year = {2013},
date = {2013-01-01},
publisher = {Springer},
keywords = {Prometeo 2012, TIASA},
pubstate = {published},
tppubtype = {book}
}
Calvo-Zaragoza, J.; Oncina, J.; Iñesta, J. M.
Recognition of Online Handwritten Music Symbols Proceedings Article
In: Proceedings of the 6th International Workshop on Machine Learning and Music, Prague, Czech Republic, 2013.
Abstract | Links | BibTeX | Tags: Prometeo 2012, TIASA
@inproceedings{k307,
title = {Recognition of Online Handwritten Music Symbols},
author = {J. Calvo-Zaragoza and J. Oncina and J. M. Iñesta},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/307/calvozaragoza-mml13.pdf},
year = {2013},
date = {2013-01-01},
urldate = {2013-01-01},
booktitle = {Proceedings of the 6th International Workshop on Machine Learning and Music},
address = {Prague, Czech Republic},
abstract = {An effective way of digitizing a new musical composition is to use an e-pen and tablet application in which the user's pen strokes are recognized online and the digital score is created with the sole effort of the composition itself. This work aims to be a starting point for research on the recognition of online handwritten music notation. To this end, different alternatives within the two modalities of recognition resulting from this data are presented: online recognition, which uses the strokes marked by a pen, and offline recognition, which uses the image generated after drawing the symbol. A comparative experiment with common machine learning algorithms over a dataset of 3800 samples and 32 different music symbols is presented. Results show that samples of the actual user are needed if good classification rates are pursued. Moreover, algorithms using the online data, on average, achieve better classifocation results than the others.},
keywords = {Prometeo 2012, TIASA},
pubstate = {published},
tppubtype = {inproceedings}
}
An effective way of digitizing a new musical composition is to use an e-pen and tablet application in which the user's pen strokes are recognized online and the digital score is created with the sole effort of the composition itself. This work aims to be a starting point for research on the recognition of online handwritten music notation. To this end, different alternatives within the two modalities of recognition resulting from this data are presented: online recognition, which uses the strokes marked by a pen, and offline recognition, which uses the image generated after drawing the symbol. A comparative experiment with common machine learning algorithms over a dataset of 3800 samples and 32 different music symbols is presented. Results show that samples of the actual user are needed if good classification rates are pursued. Moreover, algorithms using the online data, on average, achieve better classifocation results than the others.
2012
López, D.; Calera-Rubio, J.; Gallego-Sánchez, A. J.
Inference of k-Testable Directed Acyclic Graph Languages Proceedings Article
In: Journal of Machine Learning Research: Workshop and Conference Proceedings, Vol. 21: ICGI 2012, pp. 149-163, 2012.
Abstract | Links | BibTeX | Tags: PASCAL2, Prometeo 2012, TIASA
@inproceedings{k296,
title = {Inference of k-Testable Directed Acyclic Graph Languages},
author = {D. López and J. Calera-Rubio and A. J. Gallego-Sánchez},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/296/lopez12a.pdf},
year = {2012},
date = {2012-01-01},
booktitle = {Journal of Machine Learning Research: Workshop and Conference Proceedings, Vol. 21: ICGI 2012},
pages = {149-163},
abstract = {In this paper, we tackle the task of graph language learning. We first extend the well-known classes of k-testability and k-testability in the strict sense languages to directed graph languages. Second, we propose a graph automata model for directed acyclic graph languages. This graph automata model is used to 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.},
keywords = {PASCAL2, Prometeo 2012, TIASA},
pubstate = {published},
tppubtype = {inproceedings}
}
In this paper, we tackle the task of graph language learning. We first extend the well-known classes of k-testability and k-testability in the strict sense languages to directed graph languages. Second, we propose a graph automata model for directed acyclic graph languages. This graph automata model is used to 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.