MusiComb: a Sample-based Approach to Music Generation Through Constraints

Luca Giuliani, Francesco Ballerini, Allegra De Filippo, Andrea Borghesi

Abstract

Recent developments in the field of deep learning have steered research on music generation systems towards a massive use of large end-to-end neural architectures. The capability of these systems to produce convincing outputs has been extensively proven. Nonetheless, they usually come with several drawbacks, such as a low degree of user control, a lack of global structure, and the inherent impossibility of online generation due to high computational costs. Our contribution is two-fold: first, we identify these limitations and show how they have been discussed and partially addressed in the existing literature; then, we propose a novel music generation approach aimed at overcoming such limitations, by properly combining a set of samples under user-defined constraints. We model our task as a job-shop problem, and we show that interesting results can be obtained at very low computational costs. Our framework is genre-independent as it deals with samples metadata rather then individual notes, even though additional genre-specific constraint could be introduced by users to meet their stylistic requirements.
BibTeX
@inproceedings{giuliani2023musicomb,
  author = {Luca Giuliani and Francesco Ballerini and Allegra De Filippo and Andrea Borghesi},
  title = {{MusiComb: a Sample-based Approach to Music Generation Through Constraints}},
  booktitle = {ICTAI},
  year = {2023},
  doi = {10.1109/ictai59109.2023.00036},
}
Figure