Evolving Musical Sight Reading Exercises Using Expert Models

Abstract

Sight reading skills are widely considered to be crucial for all musicians. However, given that sight reading involves playing sheet music without having seen it before, once an exercise has been completed by a student it can no longer be used as a sight reading exercise for them. In this paper we present a novel evolutionary algorithm for generating musical sight reading exercises in the Western art music tradition. Using models based on expert examples, the algorithm generates material suitable for practice which is both technically appropriate and aesthetically pleasing with respect to an instrument and difficulty level. This overcomes the resource constraint in using traditional practice exercises, which are exhausted quickly by students and teachers due to their limited quantity.