Neural network-based violinist's hand animation

Abstract

We present a system for the animation of a human hand that plays violin. A neural network controls the hand movement. We make use of an optimization method to generate examples for the neural network training. The musical decision of which finger to use is automatically made by best first search. We show that the movements of the violinist's hands are physically and musically feasible, and that the musical decisions are consistent with those recommended in the violin pedagogy. A description of the system, the results of the decisions, and the animations are presented.