Composing hybrid genre music using targets derived from melodic analysis and statistical data
Date of Award
Master of Science in Computer Science
Information Systems & Computer Science
Coronel, Andrei D., Ph.D.
Algorithmically generating music using specialized algorithms is a growing focus in computer science. The success of these specialized algorithms in generating music, however, depends heavily on the fitness function that is used to score the generated music and equally as important is how the fitness function is designed. Artificial intelligence in the computational composition can use certainfeature set values derived from melodic analysis to serve as criteria for thesefitness functions. This study explores methods in how to estimate the minimumnumber of features and to define which key features to be used as fitness criteriafor algorithmic music generation of music that can be considered under a mix oftwo musical genres or hybrid-genre music. The jSymbolic tool was used to extractfeatures from musical pieces that fall under two genres. This was then reducedto a smaller feature set for use as fitness criteria. Two methods for featurereduction was explored; a decision-tree-based technique and a high-correlation filtering technique. The study was able to confirm that each technique can be used to compose hybrid-genre using up to a 89% reduced size feature-set butonly for specific genre-pairs. The study also concedes that feature-set sizes certaingenre-pair hybrids cannot be reduced past a certain threshold due to thesimilarity of the two genres.
(2017). Composing hybrid genre music using targets derived from melodic analysis and statistical data. Ateneo de Manila University.