The Evolving Drum Machine

The expectation of the listener from house and techno music seems to be that percussion sounds will maintain the same timbre for the duration of a piece of music. For the composers of such musics the synthesizing of drum sounds of a quality equal to those available from commercial drum machines or samples is difficult and seems unnecessary. A system is presented here which provides a unique method for the composition of rhythmic patterns with dynamic timbres. A genetic algorithm using a heterogeneous island population model is applied to the problem of percussion sound synthesizer design. Multiple percussion sounds are evolved simultaneously towards different targets where the targets are audio files specified by the user. The fitness function driving the evolution compares the evolving sounds to the target sounds in the frequency domain, awarding higher scores for closer matches. The system was tested using a simple step sequencer interface, as found in classic drum machines and a MIDI controlled version has also been implemented. The system provides the user (and listener) with a tangible sense of timbral transformation as the performance proceeds, where the timbres move ever closer to the target sounds. This represents an effective application of an artificial life technique to real time, algorithmically enhanced music composition.