Automatic Generation of Chord Progressions with an Artificial Immune System

• Published in: Evolutionary and Biologically Inspired Music, Sound, Art and Design Vol. 9027; pp. 175 - 186
• Main Authors: Navarro, María, Caetano, Marcelo, Bernardes, Gilberto, de Castro, Leandro Nunes, Corchado, Juan Manuel
• Format: Book Chapter
• Language: English
• Published: Switzerland Springer International Publishing AG 2015; Springer International Publishing
• Series: Lecture Notes in Computer Science
• Subjects: Algorithms & data structures; Artificial immune systems; Artificial intelligence; Chord progressions; Consonance; Harmony; User interface design & usability
• ISBN: 331916497X; 9783319164977
• ISSN: 0302-9743; 1611-3349; 1611-3349
• DOI: 10.1007/978-3-319-16498-4_16

Chord progressions are widely used in music. The automatic generation of chord progressions can be challenging because it depends on many factors, such as the musical context, personal preference, and aesthetic choices. In this work, we propose a penalty function that encodes musical rules to automatically generate chord progressions. Then we use an artificial immune system (AIS) to minimize the penalty function when proposing candidates for the next chord in a sequence. The AIS is capable of finding multiple optima in parallel, resulting in several different chords as appropriate candidates. We performed a listening test to evaluate the chords subjectively and validate the penalty function. We found that chords with a low penalty value were considered better candidates than chords with higher penalty values.