Genetic algorithms and the abc music notation language for rock music composition

Abstract

In this paper a music composition system based on genetic algorithms (GAs) will be presented. It can create multiinstrumental, guitar-orientated rock music using objective measures for its fitness functions. The output of this system is a song in the MIDI format. Along with this system, a unique conversion procedure from numerical values to the abc language (and vice versa), which allows the combination of numerical optimization with the rich expressiveness of a music description language, will be shown. The described music composition system will be further compared to other composition systems.

Data-based melody generation through multi-objective evolutionary computation

“…The most usual representation of a musical chromosome is a vector of numbers (often in binary code), representing pitch and duration information. Some authors have explored other approaches, like analytic functions (Laine and Kuuskankare 1994), languages like abc (Oliwa 2008), or motives represented by patterns (Liu and Ting 2015). More often, trees have also been used (Phon-Amnuaisuk, Law, and Ho 2007;Komatsu et al 2010;Hofmann 2015), but always in the context of a genetic programming approach, where the trees are representing a string in a language, formally represented by a syntax, so they are actually, parsing trees.…”

Data-based melody generation through multi-objective evolutionary computation

“…Some authors have explored other approaches, like analytic functions (Laine and Kuuskankare 1994), languages like abc (Oliwa 2008), or motives represented by patterns (Liu and Ting 2015). More often, trees have also been used (Phon-Amnuaisuk, Law, and Ho 2007;Komatsu et al 2010;Hofmann 2015), but always in the context of a genetic programming approach, where the trees are representing a string in a language, formally represented by a syntax, so they are actually, parsing trees.…”