Aucouturier, J.-J and Pachet, F. The influence of polyphony on the dynamical modelling of musical timbre. Pattern Recognition Letters, 28(5):654-661, 2007.

Sony CSL authors: Jean-Julien Aucouturier, François Pachet


This letter addresses the problem of pattern recognition of polyphonic musical tim- bre. Frame-level dynamics of audio features are particularly difficult to model, al- though they have been identified as crucial perceptive dimensions of timbre per- ception. Recent studies seem to indicate that traditional means to model data dy- namics, such as delta-coefficients, texture windows or Markov modelling, do not provide any improvement over the best static models for real-world, complex poly- phonic textures of several seconds’ length. This contradicts experimental data on the perception of individual instrument notes. This letter describes an experiment to identify the cause of this contradiction. We propose that the difficulty of modelling the dynamics of full songs results either from the complex structure of the temporal succession of notes, or from the vertical polyphonic nature of individual notes. We discriminate between both hypothesis by comparing the performance of static and dynamical algorithms on several specially designed datasets, namely monophonic individual notes, polyphonic individual notes, and polyphonic multiple-note tex- tures. We conclude that the main cause of the difficulty of modelling dynamics of real-world polyphonic musical textures is the polyphonic nature of the data.

Keywords: timbre


[PDF] Adobe Acrobat PDF file

BibTeX entry

@ARTICLE { aucouturier:07a, AUTHOR="Aucouturier, J.-J and Pachet, F.", JOURNAL="Pattern Recognition Letters", NUMBER="5", PAGES="654-661", TITLE="The influence of polyphony on the dynamical modelling of musical timbre", VOLUME="28", YEAR="2007", }