Challenges in creative generative models for music: a divergence maximization perspective
This addresses the limitation of creative generative models for artists and practitioners, but it is incremental as it builds on existing ML literature.
The paper tackles the problem of generative models for music being unable to create content outside their training data, proposing a new framework based on divergence maximization to address this lack of creativity.
The development of generative Machine Learning (ML) models in creative practices, enabled by the recent improvements in usability and availability of pre-trained models, is raising more and more interest among artists, practitioners and performers. Yet, the introduction of such techniques in artistic domains also revealed multiple limitations that escape current evaluation methods used by scientists. Notably, most models are still unable to generate content that lay outside of the domain defined by the training dataset. In this paper, we propose an alternative prospective framework, starting from a new general formulation of ML objectives, that we derive to delineate possible implications and solutions that already exist in the ML literature (notably for the audio and musical domain). We also discuss existing relations between generative models and computational creativity and how our framework could help address the lack of creativity in existing models.