Automatic identification of music performers with learning ensembles

Authors:
Efstathios Stamatatos;Gerhard Widmer
Affiliations:
Department of Information and Communication Systems Engineering, University of the Aegean, Samos, Greece;Department of Computational Perception, Johannes Kepler University, Linz, Austria and Austrian Research Institute for Artificial Intelligence, Vienna, Austria
Venue:
Artificial Intelligence
Year:
2005

Citing 9
Cited 3

Empirical Support for Winnow and Weighted-MajorityAlgorithms: Results on a Calendar Scheduling Domain

Machine Learning
A Comparison of Prediction Accuracy, Complexity, and Training Time of Thirty-Three Old and New Classification Algorithms

Machine Learning
An Empirical Comparison of Voting Classification Algorithms: Bagging, Boosting, and Variants

Machine Learning
Combining Classifiers with Meta Decision Trees

Machine Learning
AI and music from composition to expressive performance

AI Magazine
Discovering simple rules in complex data: a meta-learning algorithm and some surprising musical discoveries

Artificial Intelligence
In search of the Horowitz factor

AI Magazine
Using AI and machine learning to study expressive music performance: project survey and first report

AI Communications
Extracting performers' behaviors to annotate cases in a CBR system for musical tempo transformations

ICCBR'03 Proceedings of the 5th international conference on Case-based reasoning: Research and Development

Automatic performer identification in commercial monophonic Jazz performances

Pattern Recognition Letters
A state of the art on computational music performance

Expert Systems with Applications: An International Journal
A methodological contribution to music sequences analysis

ISMIS'06 Proceedings of the 16th international conference on Foundations of Intelligent Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

This article addresses the problem of identifying the most likely music performer, given a set of performances of the same piece by a number of skilled candidate pianists. We propose a set of very simple features for representing stylistic characteristics of a music performer, introducing 'norm-based' features that relate to a kind of 'average' performance. A database of piano performances of 22 pianists playing two pieces by Frederic Chopin is used in the presented experiments. Due to the limitations of the training set size and the characteristics of the input features we propose an ensemble of simple classifiers derived by both subsampling the training set and subsampling the input features. Experiments show that the proposed features are able to quantify the differences between music performers. The proposed ensemble can efficiently cope with multi-class music performer recognition under inter-piece conditions, a difficult musical task, displaying a level of accuracy unlikely to be matched by human listeners (under similar conditions).