Guide to Computing for Expressive Music Performance

pp 75-98


Expressive Performance Rendering with Probabilistic Models

  • Sebastian FlossmannAffiliated withDepartment of Computational Perception, Johannes Kepler Universitat Email author 
  • , Maarten GrachtenAffiliated withPost Doctoral Researcher at the Department of Computational Perception, Johannes Kepler University
  • , Gerhard WidmerAffiliated withDepartment of Computational Perception, Johannes Kepler University (JKU)The Austrian Research Institute for Artificial Intelligence (OFAI)

* Final gross prices may vary according to local VAT.

Get Access


We present YQX, a probabilistic performance rendering system based on Bayesian network theory. It models dependencies between score and performance and predicts performance characteristics using information extracted from the score. We discuss the basic system that won the Rendering Contest RENCON 2008 and then present several extensions, two of which aim to incorporate the current performance context into the prediction, resulting in more stable and consistent predictions. Furthermore, we describe the first steps towards a multilevel prediction model: Segmentation of the work, decomposition of tempo trajectories, and combination of different prediction models form the basis for a hierarchical prediction system. The algorithms are evaluated and compared using two very large data sets of human piano performances: 13 complete Mozart sonatas and the complete works for solo piano by Chopin.