Intelligent Generation of Rhythmic Sequences Using Finite L-systems

Maximos A. Kaliakatsos-Papakostas, Andreas Floros, Michael N. Vrahatis

Abstract: Algorithmic music synthesis with intelligent methodologies is a subject of research under both unsupervised and supervised forms, with the production of rhythm being an important aspect of the compositional process. Unsupervised algorithms tend to produce rhythms that are described either as simplistic and repetitive, or very complex and unstable. This work examines a modification of the legacy L-systems that are hereby termed as Finite L-systems (FL-systems). With this modification, the produced symbolic sequences are more controllable, offering a rhythm production alternative that is more flexible than the L-systems. In particular, when used for unsupervised rhythm production, FL-systems construct rhythmic sequences with great variability in terms of complexity and repetitiveness. This trend indicates that their combination with learning algorithms may provide a flexible supervised rhythm production system.