The process begins with a population of individuals which by some means or other produce audio (e.g. a piece, melody, or loop), which is either initialized randomly or based on human-generated music.
Then through the repeated application of computational steps analogous to biological selection, recombination and mutation the aim is for the produced audio to become more musical.
Since 1996 Rodney Waschka II has been using genetic algorithms for music composition including works such as Saint Ambrose[3] and his string quartets.
In this experiment several tens of users were first tested for their ability to recognise musical differences, and then a short piano-based melody was evolved.
Al Biles gave a tutorial on evolutionary music at GECCO 2005 and co-edited a book on the subject with contributions from many researchers in the field.