State-Based sequencing: Directing the Evolution of Music

Traditional approaches to automatic music composition do not take into account the guided nature of music, instead augmenting existing material or generating scores based on provided seed parameters. Furthermore, these approaches often use a single algorithm to create a piece, where it is more natural to split the composition process into separate musical elements. Our new State-Based Sequencer counters both of these limitations, using an agentbased collection of algorithms combined with a technique to provide motivation to the resultant music. In this paper, we describe the methodology behind this system, and provide early results from an application of the framework.