Classifier ensembles for genre recognition ∗

Previous work done in genre recognition and characterization from symbolic sources (monophonic melodies extracted from MIDI files) have pointed our research to the use of classifier ensembles to better accomplish the task. This work presents current research in the use of voting ensembles of classifiers trained on statistical description models of melodies, in order to improve both the accuracy and robustness of single classifier systems in the genre recognition task. Different voting schemes are discussed and compared, and results for a corpus of Jazz and Classical music pieces are presented and assesed.

[1]  Juan Carlos Pérez-Cortes,et al.  Musical Style Identification Using Grammatical Inference: The Encoding Problem , 2003, CIARP.

[2]  José Manuel Iñesta Quereda,et al.  Statistical description models for melody analysis and characterization , 2004, ICMC.

[3]  George Tzanetakis,et al.  Pitch Histograms in Audio and Symbolic Music Information Retrieval , 2003, ISMIR.

[4]  Jorge Calera-Rubio,et al.  Style recognition through statistical event models , 2005 .

[5]  Ludmila I. Kuncheva,et al.  That Elusive Diversity in Classifier Ensembles , 2003, IbPRIA.

[6]  Padraig Cunningham,et al.  Diversity versus Quality in Classification Ensembles Based on Feature Selection , 2000, ECML.

[7]  David W. Opitz,et al.  Generating Accurate and Diverse Members of a Neural-Network Ensemble , 1995, NIPS.

[8]  Pedro M. Domingos,et al.  Beyond Independence: Conditions for the Optimality of the Simple Bayesian Classifier , 1996, ICML.

[9]  David G. Stork,et al.  Pattern classification, 2nd Edition , 2000 .

[10]  Ichiro Fujinaga,et al.  Automatic Genre Classification Using Large High-Level Musical Feature Sets , 2004, ISMIR.

[11]  Ralph B. D'Agostino,et al.  Goodness-of-Fit-Techniques , 2020 .

[12]  Thomas M. Cover,et al.  Elements of Information Theory , 2005 .

[13]  Avrim Blum,et al.  Empirical Support for Winnow and Weighted-Majority Based Algorithms: Results on a Calendar Scheduling Domain , 1995, ICML.

[14]  Efstathios Stamatatos,et al.  Music Performer Recognition Using an Ensemble of Simple Classifiers , 2002, ECAI.

[15]  Derek Partridge,et al.  Multiple Classifier Systems: Software Engineered, Automatically Modular Leading to a Taxonomic Overview , 2002, Pattern Analysis & Applications.

[16]  Jeremy Pickens,et al.  A Survey of Feature Selection Techniques for Music Information Retrieval , 2001 .

[17]  Steve Lawrence,et al.  Artist detection in music with Minnowmatch , 2001, Neural Networks for Signal Processing XI: Proceedings of the 2001 IEEE Signal Processing Society Workshop (IEEE Cat. No.01TH8584).

[18]  Stefan M. Rüger,et al.  Robust Polyphonic Music Retrieval with N-grams , 2003, Journal of Intelligent Information Systems.

[19]  José Manuel Iñesta Quereda,et al.  Feature-Driven Recognition of Music Styles , 2003, IbPRIA.

[20]  Andrew McCallum,et al.  A comparison of event models for naive bayes text classification , 1998, AAAI 1998.

[21]  Peter Knees,et al.  Artist Classification with Web-Based Data , 2004, ISMIR.

[22]  Jiajun Zhu,et al.  Musical Genre Classification by Instrumental Features , 2004, ICMC.