Towards Evaluation of Autonomously Generated Musical Compositions: A Comprehensive Survey
Sound
2022-04-12 v1 Computers and Society
Human-Computer Interaction
Audio and Speech Processing
Abstract
There are many applications that aim to create a complete model for an autonomously generated composition; systems are able to generate muzak songs, assist singers in transcribing songs or can imitate long-dead authors. Subjective understanding of creativity or aesthetics differs not only within preferences (popular authors or genres), but also differs on the basis of experienced experience or socio-cultural environment. So, what do we want to achieve with such an adaptation? What is the benefit of the resulting work for the author, who can no longer evaluate this composition? And in what ways should we evaluate such a composition at all?
Cite
@article{arxiv.2204.04756,
title = {Towards Evaluation of Autonomously Generated Musical Compositions: A Comprehensive Survey},
author = {Daniel Kvak},
journal= {arXiv preprint arXiv:2204.04756},
year = {2022}
}