Music Performer Verification Based on Learning Ensembles
In this paper the problem of music performer verification is introduced. Given a certain performance of a musical piece and a set of candidate pianists the task is to examine whether or not a particular pianist is the actual performer. A database of 22 pianists playing pieces by F. Chopin in a computer-controlled piano is used in the presented experiments. An appropriate set of features that captures the idiosyncrasies of music performers is proposed. Well-known machine learning techniques for constructing learning ensembles are applied and remarkable results are described in verifying the actual pianist, a very difficult task even for human experts.
KeywordsBase Classifier Learn Ensemble Music Performance Speaker Verification Musical Piece
Unable to display preview. Download preview PDF.
- 3.Eisenbeis, R., Avery, R.: Discriminant Analysis and Classification Procedures: Theory and Applications. D.C. Health and Co., Lexington (1972)Google Scholar
- 7.Palmer, C.: On the Assignment of Structure in Music Performance. Music Perception 14, 23–56 (1996)Google Scholar
- 10.Stamatatos, E.: A Computational Model for Discriminating Music Performers. In: Proc. of the MOSART Workshop on Current Research Directions in Computer Music, pp. 65–69 (2001)Google Scholar
- 11.Stamatatos, E.: Quantifying the Differences Between Music Performers: Score vs. Norm. In: Proc. of the International Computer Music Conference, pp. 376–382 (2002)Google Scholar
- 14.Zanon, P., Widmer, G.: Recognition of Famous Pianists Using Machine Learning Algorithms: First Experimental Results. In: Proc. of the 14th Colloquium of Musical Informatics (2003)Google Scholar