Automated counter-melody generation for monophonic melodies

Date of Award

2017

Document Type

Thesis

Degree Name

Master of Science in Computer Science, Straight

Department

Information Systems & Computer Science

First Advisor

Coronel, Andrei D., Ph.D.

Abstract

The study aimed to create an automated process to generate counter-melodies. This was achieved by generating and deconstructing chord progressions, by assigning ratings to chords. The generated counter-melodies were then rated by an automated rubric, 10 human raters with background in music, and 10 human raters without a background in music. The counter-melodies made by this method have shown to have noticeable differences from human-made works, with a disparity in aural quality. At best the counter-melodies produced were of an average rating and far off from replacing human made works. However the results of the study are a step in the right direction.

Comments

The C7.P78 2017

Link to Full Text

Share

COinS