Toward a multilevel model of expressive piano performance
Sebastian Flossmann, Gerhard Widmer · 2011
Expressive performance modeling requires different information for each expressive dimension. Most systems, however, rely on a single approach for all dimensions. Further, tempo and timing are mostly treated as one atomic entity instead of being decomposed into elements and treated separately. We propose a performance model that discriminates expressive dimensions with regard to the modeling approach and, additionally, uses separate subsystems to model tempo and timing.