Improvisational and Interactive Systems

- Human users can guide systems to compose music according to their personal taste through rating/ranking/selecting melodies that the computer proposes.

- Human instrumentalists can improvise with computer software agents, who respond to the human's playing style.

- Evolutionary algorithms and feature extraction are crucial both for approximating the personal taste of users and for capturing the playing style of a human performer.

Selected publications:

Kaliakatsos-Papakostas, M., Floros, A., Vrahatis, M. N., "Interactive music composition driven by feature evolution", SpringerPlus, vol. 5, no. 826, 2016. (PDF)

Kaliakatsos-Papakostas, M., Epitropakis, M. G., Floros, A., and Vrahatis, M. N., "Controlling Interactive Evolution of 8–bit melodies with Genetic Programming", Soft Computing - A Fusion of Foundations, Methodologies and Applications 16, pp. 1997-2008, 2012. (PDF)

Kaliakatsos-Papakostas, M., Cambouropoulos, E., Kühnberger, K.-U., Kutz, O., Smaill, A., "Concept Invention and Music: Creating Novel Harmonies via Conceptual Blending", Proceeding of the 9th Conference on Interdisciplinary Musicology – CIM14 , 2014

Kaliakatsos-Papakostas, M., Epitropakis, M. G., Floros, A., and Vrahatis, M. N., "Interactive Evolution of 8–bit melodies with Genetic Programming towards finding aesthetic measures for sound", Applications of Evolutionary Computation, vol. 7247: Springer Berlin / Heidelberg, pp. 140–151, 2012.

Kaliakatsos-Papakostas, M., Floros, A., and Vrahatis, M. N., "Intelligent real-time music accompaniment for constraint-free improvisation", 24th IEEE International Conference on Tools with Artificial Intelligence (ICTAI 2012), pp. 444-451, 2012.