International Journal of Music Science, Technology and Art essential requirement for anyone who needs to keep up to date with new developments of music concepts throughout the world.


journal banner

IJMSTA - Vol. 1 - Issue 2 - September 2019
ISSN 2612-2146
Pages: 9

Examining the Generation of New Melodies through Generative Conceptual Blending of High-Level Features

Authors: Maximos Kaliakatsos-Papakostas
Categories: Journal

Abstract - Conceptual Blending (CB) theory discusses a basic mechanism that allows humans to understand and generate creative artefacts. CB theory has been primarily employed as a method for interpreting creative ideas and pieces of art, while recently algorithmic frameworks have been developed for methodologies that do generative use of CB towards achieving computational creativity. Regarding generative CB in music, most studies so far have focused on low-level musical information (e.g. chord roots, chord types or pitch classes) and how such information is combined to generate new musical objects (e.g. cadences) or even entire harmonic spaces. Recently, a new paradigm of CB theory has been proposed that incorporates information for high-level descriptive features of music, as pentatonicity or rhythm syncopation. The paper at hand presents results of a methodology that achieves high-level blending through low-level information recombination from input melodies using a genetic algorithm. Two evolutionary initialization schemes are presented that represent different version of CB, with and without blending completion. Specific examples are examined where Chinese Han melodies are blended with Jazz melodies and representative blends are analyzed to expose some strengths, weaknesses and possible improvements of this approach.

Keywords: Conceptual Blending, Melodic Generation, High-Level Features, Evolutionary Algorithms

Download paper

About this paper

Cite this paper as:
Kaliakatsos-Papakostas, M. (2019). Examining the Generation of New Melodies through Generative Conceptual Blending of High-Level Features. IJMSTA. 2019 Sept 1; 1 (2): 35-43.