2007
Rizo, D.; Iñesta, J. M.; León, P. J. Ponce De
Towards a human-friendly melody characterization by automatically induced rules Proceedings Article
In: Dixon, Rainer Typke David Bainbridge Simon (Ed.): Proceedings of the 8th Int. Conf. on Music Information Retrieval, ISMIR 2007, pp. 437–440, Austrian Computer Society Austrian Computer Society, Vienna, 2007, ISBN: 978-3-85403-218-2.
Abstract | Links | BibTeX | Tags: GV-JRRJ, PROSEMUS
@inproceedings{k197,
title = {Towards a human-friendly melody characterization by automatically induced rules},
author = {D. Rizo and J. M. Iñesta and P. J. Ponce De León},
editor = {Rainer Typke David Bainbridge Simon Dixon},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/197/ismir2007.pdf},
isbn = {978-3-85403-218-2},
year = {2007},
date = {2007-09-01},
urldate = {2007-09-01},
booktitle = {Proceedings of the 8th Int. Conf. on Music Information Retrieval, ISMIR 2007},
pages = {437--440},
publisher = {Austrian Computer Society},
address = {Vienna},
organization = {Austrian Computer Society},
abstract = {There is an increasing interest in music information retrieval for reference, motive, or thumbnail extraction from a piece in order to have a compact and representative representation of the information to be retrieved. One of the main references for music is its melody. In a practical environment of symbolic format collections the information can be found in standard MIDI file format, structured as a number of tracks, usually one of them containing the melodic line, while the others contain the accompaniment. The goal of this work is to analyse how statistical rules can be used to characterize a melody in such a way that one can understand the solution of an automatic system for selecting the track containing the melody in such files.},
keywords = {GV-JRRJ, PROSEMUS},
pubstate = {published},
tppubtype = {inproceedings}
}
There is an increasing interest in music information retrieval for reference, motive, or thumbnail extraction from a piece in order to have a compact and representative representation of the information to be retrieved. One of the main references for music is its melody. In a practical environment of symbolic format collections the information can be found in standard MIDI file format, structured as a number of tracks, usually one of them containing the melodic line, while the others contain the accompaniment. The goal of this work is to analyse how statistical rules can be used to characterize a melody in such a way that one can understand the solution of an automatic system for selecting the track containing the melody in such files.de León, P. J. Ponce; Iñesta, J. M.
A Pattern Recognition Approach for Music Style Identification Using Shallow Statistical Descriptors Journal Article
In: IEEE Transactions on Systems Man and Cybernetics C, vol. 37, no. 2, pp. 248-257, 2007, ISSN: 1094-6977.
Abstract | BibTeX | Tags: GV-JRRJ
@article{k179,
title = {A Pattern Recognition Approach for Music Style Identification Using Shallow Statistical Descriptors},
author = {P. J. Ponce de León and J. M. Iñesta},
issn = {1094-6977},
year = {2007},
date = {2007-01-01},
urldate = {2007-01-01},
journal = {IEEE Transactions on Systems Man and Cybernetics C},
volume = {37},
number = {2},
pages = {248-257},
abstract = {In the field of computer music, pattern recognition algorithms are very
relevant for music information retrieval (MIR) applications. One challenging
task in this area is the automatic recognition of musical style, having a
number of applications like indexing and selecting musical databases. From
melodies symbolically represented as digital scores (standard MIDI files) a
number of melodic, harmonic, and rhythmic statistical descriptors are
computed and their classification capability assessed in order to build
effective description models. A framework for experimenting in this
problem is presented, covering the feature extraction, feature selection,
and classification stages, in such a way that new features and new musical
styles can be easily incorporated and tested. Different classification
methods, like Bayesian classifier, nearest neighbors, and self-organising
maps are applied. The performance of such algorithms against different
description models and parameters is analyzed for two particular musical
styles, like jazz and classical, used as an initial benchmark for our
system.},
keywords = {GV-JRRJ},
pubstate = {published},
tppubtype = {article}
}
In the field of computer music, pattern recognition algorithms are very
relevant for music information retrieval (MIR) applications. One challenging
task in this area is the automatic recognition of musical style, having a
number of applications like indexing and selecting musical databases. From
melodies symbolically represented as digital scores (standard MIDI files) a
number of melodic, harmonic, and rhythmic statistical descriptors are
computed and their classification capability assessed in order to build
effective description models. A framework for experimenting in this
problem is presented, covering the feature extraction, feature selection,
and classification stages, in such a way that new features and new musical
styles can be easily incorporated and tested. Different classification
methods, like Bayesian classifier, nearest neighbors, and self-organising
maps are applied. The performance of such algorithms against different
description models and parameters is analyzed for two particular musical
styles, like jazz and classical, used as an initial benchmark for our
system. Pérez-Sancho, C.; León, P. J. Ponce; Espí, D.; Pertusa, A.; Rizo, D.; Iñesta, J. M.
A cooperative approach to style-oriented music composition Proceedings Article
In: Proc. of the Int. Workshop on Artificial Intelligence and Music, MUSIC-AI, pp. 25-36, Hyderabad, India, 2007.
Links | BibTeX | Tags: GV-JRRJ
@inproceedings{k186,
title = {A cooperative approach to style-oriented music composition},
author = {C. Pérez-Sancho and P. J. Ponce León and D. Espí and A. Pertusa and D. Rizo and J. M. Iñesta},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/186/wijcai07.pdf},
year = {2007},
date = {2007-01-01},
urldate = {2007-01-01},
booktitle = {Proc. of the Int. Workshop on Artificial Intelligence and Music, MUSIC-AI},
pages = {25-36},
address = {Hyderabad, India},
keywords = {GV-JRRJ},
pubstate = {published},
tppubtype = {inproceedings}
}
Moreno-Seco, F.; Micó, L.; Mazón, J. N.
New neighborhood based classification rules for metric spaces and their use in ensemble classification Journal Article
In: Lecture Notes in Computer Science, vol. 4477, no. to appear, pp. 354-361, 2007.
Abstract | BibTeX | Tags: ARFAI, GV-JRRJ
@article{k192,
title = {New neighborhood based classification rules for metric spaces and their use in ensemble classification},
author = {F. Moreno-Seco and L. Micó and J. N. Mazón},
year = {2007},
date = {2007-01-01},
urldate = {2007-01-01},
journal = {Lecture Notes in Computer Science},
volume = {4477},
number = {to appear},
pages = {354-361},
abstract = {The k-nearest-neighbor rule is a well known pattern recognition technique with very good results in a great variety of real classification
tasks. Based on the neighborhood concept, several
classification rules have been proposed to reduce the error rate of the k-nearest-neighbor rule (or its time requirements). In this work, two new geometrical neighborhoods are defined and the classification rules derived from them are used in several real data classification tasks. Also, some voting ensembles of classifiers based on these
new rules have been tested and compared.},
keywords = {ARFAI, GV-JRRJ},
pubstate = {published},
tppubtype = {article}
}
The k-nearest-neighbor rule is a well known pattern recognition technique with very good results in a great variety of real classification
tasks. Based on the neighborhood concept, several
classification rules have been proposed to reduce the error rate of the k-nearest-neighbor rule (or its time requirements). In this work, two new geometrical neighborhoods are defined and the classification rules derived from them are used in several real data classification tasks. Also, some voting ensembles of classifiers based on these
new rules have been tested and compared. Gómez-Ballester, E.; Thollard, F.; Oncina, J.
A tabular pruning rule in tree-based pruning rule fast nearest neighbour search algorithms Journal Article
In: Lecture Notes in Computer Science, vol. 4478, pp. 306-313, 2007.
Abstract | Links | BibTeX | Tags: ARFAI, GV-JRRJ
@article{k193,
title = {A tabular pruning rule in tree-based pruning rule fast nearest neighbour search algorithms},
author = {E. Gómez-Ballester and F. Thollard and J. Oncina},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/193/ibpria-eva-2007.pdf},
year = {2007},
date = {2007-01-01},
urldate = {2007-01-01},
journal = {Lecture Notes in Computer Science},
volume = {4478},
pages = {306-313},
abstract = {Some fast nearest neighbor search (NNS) algorithms using metric properties have appeared in the last years for reducing computational cost. Depending on the structure used to store the training set, different strategies to speed up the search have been defined. For instance, pruning rules avoid the search of some branches of a tree in a tree-based search algorithm. In this paper, we propose a new and simple pruning rule that can be used in most of the tree-based search algorithms.
All the information needed by the rule can be stored in a table (at preprocessing time). Moreover, the rule can be computed in constant time. This approach is evaluated through real and artificial data experiments. In order to test its performance, the rule is compared to and combined with other previously defined rules.},
keywords = {ARFAI, GV-JRRJ},
pubstate = {published},
tppubtype = {article}
}
Some fast nearest neighbor search (NNS) algorithms using metric properties have appeared in the last years for reducing computational cost. Depending on the structure used to store the training set, different strategies to speed up the search have been defined. For instance, pruning rules avoid the search of some branches of a tree in a tree-based search algorithm. In this paper, we propose a new and simple pruning rule that can be used in most of the tree-based search algorithms.
All the information needed by the rule can be stored in a table (at preprocessing time). Moreover, the rule can be computed in constant time. This approach is evaluated through real and artificial data experiments. In order to test its performance, the rule is compared to and combined with other previously defined rules. Iñesta, J. M.; Serrano, J. F.
Comparación de representaciones interválicas hansonianas para recuperación de información musical Journal Article
In: Revista Iberoamericana de Inteligencia Artificial, vol. 11, no. 34, pp. 7-15, 2007.
Abstract | BibTeX | Tags: GV-JRRJ
@article{k195,
title = {Comparación de representaciones interválicas hansonianas para recuperación de información musical},
author = {J. M. Iñesta and J. F. Serrano},
year = {2007},
date = {2007-01-01},
urldate = {2007-01-01},
journal = {Revista Iberoamericana de Inteligencia Artificial},
volume = {11},
number = {34},
pages = {7-15},
abstract = {En la recuperación de información musical se utiliza la similitud melódica como elemento principal para la detección de información relevante. Entre las aplicaciones posibles se encuentran detección de plagio de ideas ya expuestas por un artista en el pasado, el pago por derecho de autor por medio de detección de piezas musicales en transmisiones de radio, la asistencia en la composición, etc. Existen varias técnicas expuestas en similitud melódica que utilizan diversos análisis estadísticos y probabilísticos. El objetivo en este trabajo es establecer un equivalente de la notación musical a palabras de texto utilizando una representación basada en relaciones interválicas y de duración, y evaluar tres de las técnicas de recuperación de información textual aplicadas a esta representación, además de proponer cambios para mejorar el rendimiento de sistema.},
keywords = {GV-JRRJ},
pubstate = {published},
tppubtype = {article}
}
En la recuperación de información musical se utiliza la similitud melódica como elemento principal para la detección de información relevante. Entre las aplicaciones posibles se encuentran detección de plagio de ideas ya expuestas por un artista en el pasado, el pago por derecho de autor por medio de detección de piezas musicales en transmisiones de radio, la asistencia en la composición, etc. Existen varias técnicas expuestas en similitud melódica que utilizan diversos análisis estadísticos y probabilísticos. El objetivo en este trabajo es establecer un equivalente de la notación musical a palabras de texto utilizando una representación basada en relaciones interválicas y de duración, y evaluar tres de las técnicas de recuperación de información textual aplicadas a esta representación, además de proponer cambios para mejorar el rendimiento de sistema. Rico-Juan, J. R.; Iñesta, J. M.
Normalisation of confidence voting methods applied to a fast handwritten OCR classification Journal Article
In: Advances in Soft Computing. Computer Recognition Systems 2, vol. 45, pp. 405-412, 2007.
Links | BibTeX | Tags: ARFAI, GV-JRRJ
@article{k198,
title = {Normalisation of confidence voting methods applied to a fast handwritten OCR classification},
author = {J. R. Rico-Juan and J. M. Iñesta},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/198/combinacionClasificadores.pdf},
year = {2007},
date = {2007-01-01},
urldate = {2007-01-01},
journal = {Advances in Soft Computing. Computer Recognition Systems 2},
volume = {45},
pages = {405-412},
keywords = {ARFAI, GV-JRRJ},
pubstate = {published},
tppubtype = {article}
}
Iñesta, J. M.; Rizo, D.; Illescas, P. R.
Harmonic, melodic, and functional automatic analysis Proceedings Article
In: Proceedings of the 2007 International Computer Music Conferrence, pp. 165–168, 2007, ISBN: 2223-3881.
Abstract | Links | BibTeX | Tags: GV-JRRJ, PROSEMUS
@inproceedings{k201,
title = {Harmonic, melodic, and functional automatic analysis},
author = {J. M. Iñesta and D. Rizo and P. R. Illescas},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/201/icmc07_tonal_analysis.pdf},
isbn = {2223-3881},
year = {2007},
date = {2007-01-01},
urldate = {2007-01-01},
booktitle = {Proceedings of the 2007 International Computer Music Conferrence},
pages = {165--168},
abstract = {This work is an effort towards the development of a system for the automation of
traditional harmonic analysis of polyphonic scores in symbolic format. A number of stages have been
designed in this procedure: melodic analysis of harmonic and non-harmonic tones, vertical harmonic analysis, tonality, and tonal functions. All these informations are
represented as a weighted directed acyclic graph. The best possible analysis is
the path that maximizes the sum of weights in the graph, obtained through a
dynamic programming algorithm. The feasibility of this approach has been tested on six J.S. Bach's harmonized chorales},
keywords = {GV-JRRJ, PROSEMUS},
pubstate = {published},
tppubtype = {inproceedings}
}
This work is an effort towards the development of a system for the automation of
traditional harmonic analysis of polyphonic scores in symbolic format. A number of stages have been
designed in this procedure: melodic analysis of harmonic and non-harmonic tones, vertical harmonic analysis, tonality, and tonal functions. All these informations are
represented as a weighted directed acyclic graph. The best possible analysis is
the path that maximizes the sum of weights in the graph, obtained through a
dynamic programming algorithm. The feasibility of this approach has been tested on six J.S. Bach's harmonized chorales2006
Rico-Juan, J. R.; Iñesta, J. M.
An edit distance for ordered vector sets with application to character recognition Book Chapter
In: Vitria, J.; Radeva, P.; Pla, F. (Ed.): Pattern Recognition and Progress, Directions and Applications, Chapter 4, pp. 54-62, Computer Vision Center, 2006, ISBN: 84-933652-6-2.
Abstract | Links | BibTeX | Tags: GV-JRRJ
@inbook{k175,
title = {An edit distance for ordered vector sets with application to character recognition},
author = {J. R. Rico-Juan and J. M. Iñesta},
editor = {J. Vitria and P. Radeva and F. Pla},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/175/ptsdom.pdf},
isbn = {84-933652-6-2},
year = {2006},
date = {2006-03-01},
urldate = {2006-03-01},
booktitle = {Pattern Recognition and Progress, Directions and Applications},
pages = {54-62},
publisher = {Computer Vision Center},
chapter = {4},
abstract = {In this paper a new algorithm to describe a binary image as an ordered vector set is presented. An extension of the string edit distance is defined for computing it between a pair of ordered sets of vectors. This edit distance can be used in nearest neighbor classification tasks. The advantages of this method applied to isolated handwritten character classification are shown, compared to similar methods based in string or tree representations of the binary image.},
keywords = {GV-JRRJ},
pubstate = {published},
tppubtype = {inbook}
}
In this paper a new algorithm to describe a binary image as an ordered vector set is presented. An extension of the string edit distance is defined for computing it between a pair of ordered sets of vectors. This edit distance can be used in nearest neighbor classification tasks. The advantages of this method applied to isolated handwritten character classification are shown, compared to similar methods based in string or tree representations of the binary image. Pérez-Sancho, C.; León, P. J. Ponce; Rizo, D.
A Pattern Recognition Approach for Melody Track Selection in MIDI Files Proceedings Article
In: R., Tindale A. Lemström K. Dannenberg (Ed.): Proc. of the 7th Int. Symp. on Music Information Retrieval ISMIR 2006, pp. 61-66, Victoria, Canada, 2006, ISBN: 1-55058-349-2.
Abstract | BibTeX | Tags: GV-JRRJ
@inproceedings{k177,
title = {A Pattern Recognition Approach for Melody Track Selection in MIDI Files},
author = {C. Pérez-Sancho and P. J. Ponce León and D. Rizo},
editor = {Tindale A. Lemström K. Dannenberg R.},
isbn = {1-55058-349-2},
year = {2006},
date = {2006-01-01},
urldate = {2006-01-01},
booktitle = {Proc. of the 7th Int. Symp. on Music Information Retrieval ISMIR 2006},
pages = {61-66},
address = {Victoria, Canada},
abstract = {Standard MIDI files contain data that can be considered as a symbolic representation of music (a digital score), and most of them are structured as a number of tracks. One of them usually contains the melodic line of the piece, while the other tracks contain accompaniment music. The goal of this work is to identify the track that contains the melody using statistical properties of the musical content and pattern recognition techniques.
Finding that track is very useful for a number of applications, like speeding up melody matching when searching in MIDI databases or motif extraction, among others. First, a set of descriptors from each track of the target file are extracted. These descriptors are the input to a random forest classifier
that assigns the probability of being a melodic line to each track. The track with the highest probability is selected as the one containing the melodic line of that MIDI file. Promising results have been obtained testing a number of databases of different music styles.},
keywords = {GV-JRRJ},
pubstate = {published},
tppubtype = {inproceedings}
}
Standard MIDI files contain data that can be considered as a symbolic representation of music (a digital score), and most of them are structured as a number of tracks. One of them usually contains the melodic line of the piece, while the other tracks contain accompaniment music. The goal of this work is to identify the track that contains the melody using statistical properties of the musical content and pattern recognition techniques.
Finding that track is very useful for a number of applications, like speeding up melody matching when searching in MIDI databases or motif extraction, among others. First, a set of descriptors from each track of the target file are extracted. These descriptors are the input to a random forest classifier
that assigns the probability of being a melodic line to each track. The track with the highest probability is selected as the one containing the melodic line of that MIDI file. Promising results have been obtained testing a number of databases of different music styles. Moreno-Seco, F.; Iñesta, J. M.; León, P. J. Ponce; Micó, L.
Comparison of Classifier Fusion Methods for Classification in Pattern Recognition Tasks Journal Article
In: Lecture Notes in Computer Science, vol. 4109, pp. 705–713, 2006.
Abstract | Links | BibTeX | Tags: GV-JRRJ
@article{k181,
title = {Comparison of Classifier Fusion Methods for Classification in Pattern Recognition Tasks},
author = {F. Moreno-Seco and J. M. Iñesta and P. J. Ponce León and L. Micó},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/181/spr-p183.pdf},
year = {2006},
date = {2006-01-01},
urldate = {2006-01-01},
journal = {Lecture Notes in Computer Science},
volume = {4109},
pages = {705--713},
abstract = {This work presents a comparison of current research in the use of voting ensembles of classifiers in order to improve the accuracy of single classifiers and make the performance more robust against the difficulties that each individual classifier may have. Also, a number of combination rules are proposed. Different voting schemes are discussed and compared in order to study the performance of the ensemble in each task. The ensembles have been trained on real data available for benchmarking and also applied to a case study related to statistical description models of melodies for music genre recognition.},
keywords = {GV-JRRJ},
pubstate = {published},
tppubtype = {article}
}
This work presents a comparison of current research in the use of voting ensembles of classifiers in order to improve the accuracy of single classifiers and make the performance more robust against the difficulties that each individual classifier may have. Also, a number of combination rules are proposed. Different voting schemes are discussed and compared in order to study the performance of the ensemble in each task. The ensembles have been trained on real data available for benchmarking and also applied to a case study related to statistical description models of melodies for music genre recognition. Serrano, J. F.; Iñesta, J. M.
Comparison of Hanson intervallic representations for music information retrieval Proceedings Article
In: Suárez-Guerra, A. Gelbuck S. (Ed.): Proc. of the 15th Int. Conf. on Computing (CIC-2006), pp. 147-153, IEEE computer society press, 2006, ISBN: 0-7695-2708-6.
@inproceedings{k183,
title = {Comparison of Hanson intervallic representations for music information retrieval},
author = {J. F. Serrano and J. M. Iñesta},
editor = {A. Gelbuck S. Suárez-Guerra},
isbn = {0-7695-2708-6},
year = {2006},
date = {2006-01-01},
booktitle = {Proc. of the 15th Int. Conf. on Computing (CIC-2006)},
pages = {147-153},
publisher = {IEEE computer society press},
keywords = {GV-JRRJ},
pubstate = {published},
tppubtype = {inproceedings}
}
Serrano, J. F.; Iñesta, J. M.
Music motive extraction through Hanson intervallic analysis Proceedings Article
In: Suárez-Guerra, A. Gelbuck S. (Ed.): Proc. of the 15th Int. Conf. on Computing (CIC-2006), pp. 154-160, IEEE computer society press, 2006, ISBN: 0-7695-2708-6.
@inproceedings{k184,
title = {Music motive extraction through Hanson intervallic analysis},
author = {J. F. Serrano and J. M. Iñesta},
editor = {A. Gelbuck S. Suárez-Guerra},
isbn = {0-7695-2708-6},
year = {2006},
date = {2006-01-01},
booktitle = {Proc. of the 15th Int. Conf. on Computing (CIC-2006)},
pages = {154-160},
publisher = {IEEE computer society press},
keywords = {GV-JRRJ},
pubstate = {published},
tppubtype = {inproceedings}
}
2007
Rizo, D.; Iñesta, J. M.; León, P. J. Ponce De
Towards a human-friendly melody characterization by automatically induced rules Proceedings Article
In: Dixon, Rainer Typke David Bainbridge Simon (Ed.): Proceedings of the 8th Int. Conf. on Music Information Retrieval, ISMIR 2007, pp. 437–440, Austrian Computer Society Austrian Computer Society, Vienna, 2007, ISBN: 978-3-85403-218-2.
Abstract | Links | BibTeX | Tags: GV-JRRJ, PROSEMUS
@inproceedings{k197,
title = {Towards a human-friendly melody characterization by automatically induced rules},
author = {D. Rizo and J. M. Iñesta and P. J. Ponce De León},
editor = {Rainer Typke David Bainbridge Simon Dixon},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/197/ismir2007.pdf},
isbn = {978-3-85403-218-2},
year = {2007},
date = {2007-09-01},
urldate = {2007-09-01},
booktitle = {Proceedings of the 8th Int. Conf. on Music Information Retrieval, ISMIR 2007},
pages = {437--440},
publisher = {Austrian Computer Society},
address = {Vienna},
organization = {Austrian Computer Society},
abstract = {There is an increasing interest in music information retrieval for reference, motive, or thumbnail extraction from a piece in order to have a compact and representative representation of the information to be retrieved. One of the main references for music is its melody. In a practical environment of symbolic format collections the information can be found in standard MIDI file format, structured as a number of tracks, usually one of them containing the melodic line, while the others contain the accompaniment. The goal of this work is to analyse how statistical rules can be used to characterize a melody in such a way that one can understand the solution of an automatic system for selecting the track containing the melody in such files.},
keywords = {GV-JRRJ, PROSEMUS},
pubstate = {published},
tppubtype = {inproceedings}
}
There is an increasing interest in music information retrieval for reference, motive, or thumbnail extraction from a piece in order to have a compact and representative representation of the information to be retrieved. One of the main references for music is its melody. In a practical environment of symbolic format collections the information can be found in standard MIDI file format, structured as a number of tracks, usually one of them containing the melodic line, while the others contain the accompaniment. The goal of this work is to analyse how statistical rules can be used to characterize a melody in such a way that one can understand the solution of an automatic system for selecting the track containing the melody in such files.
de León, P. J. Ponce; Iñesta, J. M.
A Pattern Recognition Approach for Music Style Identification Using Shallow Statistical Descriptors Journal Article
In: IEEE Transactions on Systems Man and Cybernetics C, vol. 37, no. 2, pp. 248-257, 2007, ISSN: 1094-6977.
Abstract | BibTeX | Tags: GV-JRRJ
@article{k179,
title = {A Pattern Recognition Approach for Music Style Identification Using Shallow Statistical Descriptors},
author = {P. J. Ponce de León and J. M. Iñesta},
issn = {1094-6977},
year = {2007},
date = {2007-01-01},
urldate = {2007-01-01},
journal = {IEEE Transactions on Systems Man and Cybernetics C},
volume = {37},
number = {2},
pages = {248-257},
abstract = {In the field of computer music, pattern recognition algorithms are very
relevant for music information retrieval (MIR) applications. One challenging
task in this area is the automatic recognition of musical style, having a
number of applications like indexing and selecting musical databases. From
melodies symbolically represented as digital scores (standard MIDI files) a
number of melodic, harmonic, and rhythmic statistical descriptors are
computed and their classification capability assessed in order to build
effective description models. A framework for experimenting in this
problem is presented, covering the feature extraction, feature selection,
and classification stages, in such a way that new features and new musical
styles can be easily incorporated and tested. Different classification
methods, like Bayesian classifier, nearest neighbors, and self-organising
maps are applied. The performance of such algorithms against different
description models and parameters is analyzed for two particular musical
styles, like jazz and classical, used as an initial benchmark for our
system.},
keywords = {GV-JRRJ},
pubstate = {published},
tppubtype = {article}
}
In the field of computer music, pattern recognition algorithms are very
relevant for music information retrieval (MIR) applications. One challenging
task in this area is the automatic recognition of musical style, having a
number of applications like indexing and selecting musical databases. From
melodies symbolically represented as digital scores (standard MIDI files) a
number of melodic, harmonic, and rhythmic statistical descriptors are
computed and their classification capability assessed in order to build
effective description models. A framework for experimenting in this
problem is presented, covering the feature extraction, feature selection,
and classification stages, in such a way that new features and new musical
styles can be easily incorporated and tested. Different classification
methods, like Bayesian classifier, nearest neighbors, and self-organising
maps are applied. The performance of such algorithms against different
description models and parameters is analyzed for two particular musical
styles, like jazz and classical, used as an initial benchmark for our
system.
relevant for music information retrieval (MIR) applications. One challenging
task in this area is the automatic recognition of musical style, having a
number of applications like indexing and selecting musical databases. From
melodies symbolically represented as digital scores (standard MIDI files) a
number of melodic, harmonic, and rhythmic statistical descriptors are
computed and their classification capability assessed in order to build
effective description models. A framework for experimenting in this
problem is presented, covering the feature extraction, feature selection,
and classification stages, in such a way that new features and new musical
styles can be easily incorporated and tested. Different classification
methods, like Bayesian classifier, nearest neighbors, and self-organising
maps are applied. The performance of such algorithms against different
description models and parameters is analyzed for two particular musical
styles, like jazz and classical, used as an initial benchmark for our
system.
Pérez-Sancho, C.; León, P. J. Ponce; Espí, D.; Pertusa, A.; Rizo, D.; Iñesta, J. M.
A cooperative approach to style-oriented music composition Proceedings Article
In: Proc. of the Int. Workshop on Artificial Intelligence and Music, MUSIC-AI, pp. 25-36, Hyderabad, India, 2007.
Links | BibTeX | Tags: GV-JRRJ
@inproceedings{k186,
title = {A cooperative approach to style-oriented music composition},
author = {C. Pérez-Sancho and P. J. Ponce León and D. Espí and A. Pertusa and D. Rizo and J. M. Iñesta},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/186/wijcai07.pdf},
year = {2007},
date = {2007-01-01},
urldate = {2007-01-01},
booktitle = {Proc. of the Int. Workshop on Artificial Intelligence and Music, MUSIC-AI},
pages = {25-36},
address = {Hyderabad, India},
keywords = {GV-JRRJ},
pubstate = {published},
tppubtype = {inproceedings}
}
Moreno-Seco, F.; Micó, L.; Mazón, J. N.
New neighborhood based classification rules for metric spaces and their use in ensemble classification Journal Article
In: Lecture Notes in Computer Science, vol. 4477, no. to appear, pp. 354-361, 2007.
Abstract | BibTeX | Tags: ARFAI, GV-JRRJ
@article{k192,
title = {New neighborhood based classification rules for metric spaces and their use in ensemble classification},
author = {F. Moreno-Seco and L. Micó and J. N. Mazón},
year = {2007},
date = {2007-01-01},
urldate = {2007-01-01},
journal = {Lecture Notes in Computer Science},
volume = {4477},
number = {to appear},
pages = {354-361},
abstract = {The k-nearest-neighbor rule is a well known pattern recognition technique with very good results in a great variety of real classification
tasks. Based on the neighborhood concept, several
classification rules have been proposed to reduce the error rate of the k-nearest-neighbor rule (or its time requirements). In this work, two new geometrical neighborhoods are defined and the classification rules derived from them are used in several real data classification tasks. Also, some voting ensembles of classifiers based on these
new rules have been tested and compared.},
keywords = {ARFAI, GV-JRRJ},
pubstate = {published},
tppubtype = {article}
}
The k-nearest-neighbor rule is a well known pattern recognition technique with very good results in a great variety of real classification
tasks. Based on the neighborhood concept, several
classification rules have been proposed to reduce the error rate of the k-nearest-neighbor rule (or its time requirements). In this work, two new geometrical neighborhoods are defined and the classification rules derived from them are used in several real data classification tasks. Also, some voting ensembles of classifiers based on these
new rules have been tested and compared.
tasks. Based on the neighborhood concept, several
classification rules have been proposed to reduce the error rate of the k-nearest-neighbor rule (or its time requirements). In this work, two new geometrical neighborhoods are defined and the classification rules derived from them are used in several real data classification tasks. Also, some voting ensembles of classifiers based on these
new rules have been tested and compared.
Gómez-Ballester, E.; Thollard, F.; Oncina, J.
A tabular pruning rule in tree-based pruning rule fast nearest neighbour search algorithms Journal Article
In: Lecture Notes in Computer Science, vol. 4478, pp. 306-313, 2007.
Abstract | Links | BibTeX | Tags: ARFAI, GV-JRRJ
@article{k193,
title = {A tabular pruning rule in tree-based pruning rule fast nearest neighbour search algorithms},
author = {E. Gómez-Ballester and F. Thollard and J. Oncina},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/193/ibpria-eva-2007.pdf},
year = {2007},
date = {2007-01-01},
urldate = {2007-01-01},
journal = {Lecture Notes in Computer Science},
volume = {4478},
pages = {306-313},
abstract = {Some fast nearest neighbor search (NNS) algorithms using metric properties have appeared in the last years for reducing computational cost. Depending on the structure used to store the training set, different strategies to speed up the search have been defined. For instance, pruning rules avoid the search of some branches of a tree in a tree-based search algorithm. In this paper, we propose a new and simple pruning rule that can be used in most of the tree-based search algorithms.
All the information needed by the rule can be stored in a table (at preprocessing time). Moreover, the rule can be computed in constant time. This approach is evaluated through real and artificial data experiments. In order to test its performance, the rule is compared to and combined with other previously defined rules.},
keywords = {ARFAI, GV-JRRJ},
pubstate = {published},
tppubtype = {article}
}
Some fast nearest neighbor search (NNS) algorithms using metric properties have appeared in the last years for reducing computational cost. Depending on the structure used to store the training set, different strategies to speed up the search have been defined. For instance, pruning rules avoid the search of some branches of a tree in a tree-based search algorithm. In this paper, we propose a new and simple pruning rule that can be used in most of the tree-based search algorithms.
All the information needed by the rule can be stored in a table (at preprocessing time). Moreover, the rule can be computed in constant time. This approach is evaluated through real and artificial data experiments. In order to test its performance, the rule is compared to and combined with other previously defined rules.
All the information needed by the rule can be stored in a table (at preprocessing time). Moreover, the rule can be computed in constant time. This approach is evaluated through real and artificial data experiments. In order to test its performance, the rule is compared to and combined with other previously defined rules.
Iñesta, J. M.; Serrano, J. F.
Comparación de representaciones interválicas hansonianas para recuperación de información musical Journal Article
In: Revista Iberoamericana de Inteligencia Artificial, vol. 11, no. 34, pp. 7-15, 2007.
Abstract | BibTeX | Tags: GV-JRRJ
@article{k195,
title = {Comparación de representaciones interválicas hansonianas para recuperación de información musical},
author = {J. M. Iñesta and J. F. Serrano},
year = {2007},
date = {2007-01-01},
urldate = {2007-01-01},
journal = {Revista Iberoamericana de Inteligencia Artificial},
volume = {11},
number = {34},
pages = {7-15},
abstract = {En la recuperación de información musical se utiliza la similitud melódica como elemento principal para la detección de información relevante. Entre las aplicaciones posibles se encuentran detección de plagio de ideas ya expuestas por un artista en el pasado, el pago por derecho de autor por medio de detección de piezas musicales en transmisiones de radio, la asistencia en la composición, etc. Existen varias técnicas expuestas en similitud melódica que utilizan diversos análisis estadísticos y probabilísticos. El objetivo en este trabajo es establecer un equivalente de la notación musical a palabras de texto utilizando una representación basada en relaciones interválicas y de duración, y evaluar tres de las técnicas de recuperación de información textual aplicadas a esta representación, además de proponer cambios para mejorar el rendimiento de sistema.},
keywords = {GV-JRRJ},
pubstate = {published},
tppubtype = {article}
}
En la recuperación de información musical se utiliza la similitud melódica como elemento principal para la detección de información relevante. Entre las aplicaciones posibles se encuentran detección de plagio de ideas ya expuestas por un artista en el pasado, el pago por derecho de autor por medio de detección de piezas musicales en transmisiones de radio, la asistencia en la composición, etc. Existen varias técnicas expuestas en similitud melódica que utilizan diversos análisis estadísticos y probabilísticos. El objetivo en este trabajo es establecer un equivalente de la notación musical a palabras de texto utilizando una representación basada en relaciones interválicas y de duración, y evaluar tres de las técnicas de recuperación de información textual aplicadas a esta representación, además de proponer cambios para mejorar el rendimiento de sistema.
Rico-Juan, J. R.; Iñesta, J. M.
Normalisation of confidence voting methods applied to a fast handwritten OCR classification Journal Article
In: Advances in Soft Computing. Computer Recognition Systems 2, vol. 45, pp. 405-412, 2007.
Links | BibTeX | Tags: ARFAI, GV-JRRJ
@article{k198,
title = {Normalisation of confidence voting methods applied to a fast handwritten OCR classification},
author = {J. R. Rico-Juan and J. M. Iñesta},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/198/combinacionClasificadores.pdf},
year = {2007},
date = {2007-01-01},
urldate = {2007-01-01},
journal = {Advances in Soft Computing. Computer Recognition Systems 2},
volume = {45},
pages = {405-412},
keywords = {ARFAI, GV-JRRJ},
pubstate = {published},
tppubtype = {article}
}
Iñesta, J. M.; Rizo, D.; Illescas, P. R.
Harmonic, melodic, and functional automatic analysis Proceedings Article
In: Proceedings of the 2007 International Computer Music Conferrence, pp. 165–168, 2007, ISBN: 2223-3881.
Abstract | Links | BibTeX | Tags: GV-JRRJ, PROSEMUS
@inproceedings{k201,
title = {Harmonic, melodic, and functional automatic analysis},
author = {J. M. Iñesta and D. Rizo and P. R. Illescas},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/201/icmc07_tonal_analysis.pdf},
isbn = {2223-3881},
year = {2007},
date = {2007-01-01},
urldate = {2007-01-01},
booktitle = {Proceedings of the 2007 International Computer Music Conferrence},
pages = {165--168},
abstract = {This work is an effort towards the development of a system for the automation of
traditional harmonic analysis of polyphonic scores in symbolic format. A number of stages have been
designed in this procedure: melodic analysis of harmonic and non-harmonic tones, vertical harmonic analysis, tonality, and tonal functions. All these informations are
represented as a weighted directed acyclic graph. The best possible analysis is
the path that maximizes the sum of weights in the graph, obtained through a
dynamic programming algorithm. The feasibility of this approach has been tested on six J.S. Bach's harmonized chorales},
keywords = {GV-JRRJ, PROSEMUS},
pubstate = {published},
tppubtype = {inproceedings}
}
This work is an effort towards the development of a system for the automation of
traditional harmonic analysis of polyphonic scores in symbolic format. A number of stages have been
designed in this procedure: melodic analysis of harmonic and non-harmonic tones, vertical harmonic analysis, tonality, and tonal functions. All these informations are
represented as a weighted directed acyclic graph. The best possible analysis is
the path that maximizes the sum of weights in the graph, obtained through a
dynamic programming algorithm. The feasibility of this approach has been tested on six J.S. Bach's harmonized chorales
traditional harmonic analysis of polyphonic scores in symbolic format. A number of stages have been
designed in this procedure: melodic analysis of harmonic and non-harmonic tones, vertical harmonic analysis, tonality, and tonal functions. All these informations are
represented as a weighted directed acyclic graph. The best possible analysis is
the path that maximizes the sum of weights in the graph, obtained through a
dynamic programming algorithm. The feasibility of this approach has been tested on six J.S. Bach's harmonized chorales
2006
Rico-Juan, J. R.; Iñesta, J. M.
An edit distance for ordered vector sets with application to character recognition Book Chapter
In: Vitria, J.; Radeva, P.; Pla, F. (Ed.): Pattern Recognition and Progress, Directions and Applications, Chapter 4, pp. 54-62, Computer Vision Center, 2006, ISBN: 84-933652-6-2.
Abstract | Links | BibTeX | Tags: GV-JRRJ
@inbook{k175,
title = {An edit distance for ordered vector sets with application to character recognition},
author = {J. R. Rico-Juan and J. M. Iñesta},
editor = {J. Vitria and P. Radeva and F. Pla},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/175/ptsdom.pdf},
isbn = {84-933652-6-2},
year = {2006},
date = {2006-03-01},
urldate = {2006-03-01},
booktitle = {Pattern Recognition and Progress, Directions and Applications},
pages = {54-62},
publisher = {Computer Vision Center},
chapter = {4},
abstract = {In this paper a new algorithm to describe a binary image as an ordered vector set is presented. An extension of the string edit distance is defined for computing it between a pair of ordered sets of vectors. This edit distance can be used in nearest neighbor classification tasks. The advantages of this method applied to isolated handwritten character classification are shown, compared to similar methods based in string or tree representations of the binary image.},
keywords = {GV-JRRJ},
pubstate = {published},
tppubtype = {inbook}
}
In this paper a new algorithm to describe a binary image as an ordered vector set is presented. An extension of the string edit distance is defined for computing it between a pair of ordered sets of vectors. This edit distance can be used in nearest neighbor classification tasks. The advantages of this method applied to isolated handwritten character classification are shown, compared to similar methods based in string or tree representations of the binary image.
Pérez-Sancho, C.; León, P. J. Ponce; Rizo, D.
A Pattern Recognition Approach for Melody Track Selection in MIDI Files Proceedings Article
In: R., Tindale A. Lemström K. Dannenberg (Ed.): Proc. of the 7th Int. Symp. on Music Information Retrieval ISMIR 2006, pp. 61-66, Victoria, Canada, 2006, ISBN: 1-55058-349-2.
Abstract | BibTeX | Tags: GV-JRRJ
@inproceedings{k177,
title = {A Pattern Recognition Approach for Melody Track Selection in MIDI Files},
author = {C. Pérez-Sancho and P. J. Ponce León and D. Rizo},
editor = {Tindale A. Lemström K. Dannenberg R.},
isbn = {1-55058-349-2},
year = {2006},
date = {2006-01-01},
urldate = {2006-01-01},
booktitle = {Proc. of the 7th Int. Symp. on Music Information Retrieval ISMIR 2006},
pages = {61-66},
address = {Victoria, Canada},
abstract = {Standard MIDI files contain data that can be considered as a symbolic representation of music (a digital score), and most of them are structured as a number of tracks. One of them usually contains the melodic line of the piece, while the other tracks contain accompaniment music. The goal of this work is to identify the track that contains the melody using statistical properties of the musical content and pattern recognition techniques.
Finding that track is very useful for a number of applications, like speeding up melody matching when searching in MIDI databases or motif extraction, among others. First, a set of descriptors from each track of the target file are extracted. These descriptors are the input to a random forest classifier
that assigns the probability of being a melodic line to each track. The track with the highest probability is selected as the one containing the melodic line of that MIDI file. Promising results have been obtained testing a number of databases of different music styles.},
keywords = {GV-JRRJ},
pubstate = {published},
tppubtype = {inproceedings}
}
Standard MIDI files contain data that can be considered as a symbolic representation of music (a digital score), and most of them are structured as a number of tracks. One of them usually contains the melodic line of the piece, while the other tracks contain accompaniment music. The goal of this work is to identify the track that contains the melody using statistical properties of the musical content and pattern recognition techniques.
Finding that track is very useful for a number of applications, like speeding up melody matching when searching in MIDI databases or motif extraction, among others. First, a set of descriptors from each track of the target file are extracted. These descriptors are the input to a random forest classifier
that assigns the probability of being a melodic line to each track. The track with the highest probability is selected as the one containing the melodic line of that MIDI file. Promising results have been obtained testing a number of databases of different music styles.
Finding that track is very useful for a number of applications, like speeding up melody matching when searching in MIDI databases or motif extraction, among others. First, a set of descriptors from each track of the target file are extracted. These descriptors are the input to a random forest classifier
that assigns the probability of being a melodic line to each track. The track with the highest probability is selected as the one containing the melodic line of that MIDI file. Promising results have been obtained testing a number of databases of different music styles.
Moreno-Seco, F.; Iñesta, J. M.; León, P. J. Ponce; Micó, L.
Comparison of Classifier Fusion Methods for Classification in Pattern Recognition Tasks Journal Article
In: Lecture Notes in Computer Science, vol. 4109, pp. 705–713, 2006.
Abstract | Links | BibTeX | Tags: GV-JRRJ
@article{k181,
title = {Comparison of Classifier Fusion Methods for Classification in Pattern Recognition Tasks},
author = {F. Moreno-Seco and J. M. Iñesta and P. J. Ponce León and L. Micó},
url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/181/spr-p183.pdf},
year = {2006},
date = {2006-01-01},
urldate = {2006-01-01},
journal = {Lecture Notes in Computer Science},
volume = {4109},
pages = {705--713},
abstract = {This work presents a comparison of current research in the use of voting ensembles of classifiers in order to improve the accuracy of single classifiers and make the performance more robust against the difficulties that each individual classifier may have. Also, a number of combination rules are proposed. Different voting schemes are discussed and compared in order to study the performance of the ensemble in each task. The ensembles have been trained on real data available for benchmarking and also applied to a case study related to statistical description models of melodies for music genre recognition.},
keywords = {GV-JRRJ},
pubstate = {published},
tppubtype = {article}
}
This work presents a comparison of current research in the use of voting ensembles of classifiers in order to improve the accuracy of single classifiers and make the performance more robust against the difficulties that each individual classifier may have. Also, a number of combination rules are proposed. Different voting schemes are discussed and compared in order to study the performance of the ensemble in each task. The ensembles have been trained on real data available for benchmarking and also applied to a case study related to statistical description models of melodies for music genre recognition.
Serrano, J. F.; Iñesta, J. M.
Comparison of Hanson intervallic representations for music information retrieval Proceedings Article
In: Suárez-Guerra, A. Gelbuck S. (Ed.): Proc. of the 15th Int. Conf. on Computing (CIC-2006), pp. 147-153, IEEE computer society press, 2006, ISBN: 0-7695-2708-6.
@inproceedings{k183,
title = {Comparison of Hanson intervallic representations for music information retrieval},
author = {J. F. Serrano and J. M. Iñesta},
editor = {A. Gelbuck S. Suárez-Guerra},
isbn = {0-7695-2708-6},
year = {2006},
date = {2006-01-01},
booktitle = {Proc. of the 15th Int. Conf. on Computing (CIC-2006)},
pages = {147-153},
publisher = {IEEE computer society press},
keywords = {GV-JRRJ},
pubstate = {published},
tppubtype = {inproceedings}
}
Serrano, J. F.; Iñesta, J. M.
Music motive extraction through Hanson intervallic analysis Proceedings Article
In: Suárez-Guerra, A. Gelbuck S. (Ed.): Proc. of the 15th Int. Conf. on Computing (CIC-2006), pp. 154-160, IEEE computer society press, 2006, ISBN: 0-7695-2708-6.
@inproceedings{k184,
title = {Music motive extraction through Hanson intervallic analysis},
author = {J. F. Serrano and J. M. Iñesta},
editor = {A. Gelbuck S. Suárez-Guerra},
isbn = {0-7695-2708-6},
year = {2006},
date = {2006-01-01},
booktitle = {Proc. of the 15th Int. Conf. on Computing (CIC-2006)},
pages = {154-160},
publisher = {IEEE computer society press},
keywords = {GV-JRRJ},
pubstate = {published},
tppubtype = {inproceedings}
}