Mira, Rodrigo, Coutinho, E, Parada-Cabaleiro, Emilia and Schuller, Bjoern
(2023)
Automated composition of Galician Xota - tuning RNN-based composers for specific musical styles using Deep Q-Learning.
PeerJ Computer Science, 9.
e1356-.
|
Text
Automated composition of Galician Xota-tuning RNN-based composers for specific musical styles using deep Q-learning.pdf - Open Access published version Download (2MB) | Preview |
Abstract
Music composition is a complex field that is difficult to automate because the computational definition of what is good or aesthetically pleasing is vague and subjective. Many neural network-based methods have been applied in the past, but they lack consistency and in most cases, their outputs fail to impress. The most common issues include excessive repetition and a lack of style and structure, which are hallmarks of artificial compositions. In this project, we build on a model created by Magenta-the RL Tuner-extending it to emulate a specific musical genre-the <i>Galician Xota</i>. To do this, we design a new rule-set containing rules that the composition should follow to adhere to this style. We then implement them using reward functions, which are used to train the Deep Q Network that will be used to generate the pieces. After extensive experimentation, we achieve an implementation of our rule-set that effectively enforces each rule on the generated compositions, and outline a solid research methodology for future researchers looking to use this architecture. Finally, we propose some promising future work regarding further applications for this model and improvements to the experimental procedure.
| Item Type: | Article |
|---|---|
| Uncontrolled Keywords: | Automated music composition, Galician Xota, Magenta, RL Tuner, Deep Q-Learning |
| Divisions: | Faculty of Humanities and Social Sciences > School of the Arts |
| Depositing User: | Symplectic Admin |
| Date Deposited: | 31 Mar 2023 07:30 |
| Last Modified: | 21 Mar 2024 15:59 |
| DOI: | 10.7717/peerj-cs.1356 |
| Related URLs: | |
| URI: | https://livrepository.liverpool.ac.uk/id/eprint/3169367 |
Dimensions
Dimensions
