Challenges in creative generative models for music: a divergence maximization perspective. (arXiv:2211.08856v1 [stat.ML])

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 …

arxiv challenges creative divergence generative models music perspective