In this chapter, recent research in the domain of melodic harmonization and computational creativity is presented with a view to highlighting strengths and weaknesses of the classical cognitively inspired symbolic AI approach (often in juxtaposition to contemporary deep learning methodologies). A modular melodic harmonization system that learns chord types, chord transitions, cadences, and bassline voice leading from diverse harmonic datasets is presented. Then, it is shown that the harmonic knowledge acquired by this system can be used creatively in a cognitively inspired conceptual blending model that creates novel harmonic spaces, combining in meaningful ways the various harmonic components of different styles. This system is essentially a proof-of-concept creative model that demonstrates that new concepts can be invented which transcend the initial harmonic input spaces. It is argued that such original creativity is more naturally accommodated in the world of symbolic reasoning that allows links and inferences between diverse concepts at highly abstract levels. Moreover, symbolic representations and processing facilitate interpretability and explanation that are key components of musical knowledge advancement. Finally, reconciling symbolic AI with deep learning may be the way forward to combine the strengths of both approaches toward building more sophisticated robust musical systems that connect sensory auditory data to abstract musical concepts.
CITATION STYLE
Cambouropoulos, E., & Kaliakatsos-Papakostas, M. (2021). Cognitive Musicology and Artificial Intelligence: Harmonic Analysis, Learning, and Generation. In Handbook of Artificial Intelligence for Music: Foundations, Advanced Approaches, and Developments for Creativity (pp. 263–281). Springer International Publishing. https://doi.org/10.1007/978-3-030-72116-9_10
Mendeley helps you to discover research relevant for your work.