Generative Deep Learning for Virtuosic Classical Music: Generative Adversarial Networks as Renowned Composers
This research tackles the problem of creating high-quality, human-like classical music compositions for musicians and AI music generation researchers, representing an incremental step in the field.
The paper addresses the lack of fundamental compositional techniques in AI-generated music. It aims to identify necessary parameters for generating compositions nearly indistinguishable from those of master composers by narrowing down programmatic and musical implementation issues.
Current AI-generated music lacks fundamental principles of good compositional techniques. By narrowing down implementation issues both programmatically and musically, we can create a better understanding of what parameters are necessary for a generated composition nearly indistinguishable from that of a master composer.