Documentdetail
ID kaart
oai:arXiv.org:2410.10515
Onderwerp
Computer Science - Sound Computer Science - Machine Learnin... Electrical Engineering and Systems...Auteur
Souza, Gabriel Figueiredo, Flavio Machado, Alexei Guimarães, DeborahCategorie
Computer Science
Jaar
2024
vermelding datum
16-10-2024
Trefwoorden
learning models science musicBeschrijving
In recent years, deep learning has achieved formidable results in creative computing.
When it comes to music, one viable model for music generation are Transformer based models.
However, while transformers models are popular for music generation, they often rely on annotated structural information.
In this work, we inquire if the off-the-shelf Music Transformer models perform just as well on structural similarity metrics using only unannotated MIDI information.
We show that a slight tweak to the most common representation yields small but significant improvements.
We also advocate that searching for better unannotated musical representations is more cost-effective than producing large amounts of curated and annotated data.
;Comment: Presented at the Music for Machine Learning Workshop with ECML/PKDD.
To be published by Springer
Souza, Gabriel,Figueiredo, Flavio,Machado, Alexei,Guimarães, Deborah, 2024, Do we need more complex representations for structure? A comparison of note duration representation for Music Transformers
Choice Between Partial Trajectories: Disentangling Goals from Beliefs
agents models aligned based bootstrapped learning reward function model return choice choices partial
Adverse and serious adverse events incidence of pharmacological interventions for managing chronic and episodic migraine in adults: a systematic review
aes medications bta incidence migraine drugs disorders
