The Chordinator: Chord progression modeling and generation using transformers - Archive ouverte HAL Accéder directement au contenu
Autre Publication Scientifique Année : 2023

The Chordinator: Chord progression modeling and generation using transformers

Résumé

This paper presents a transformer model trained with a large dataset of chord sequences. The dataset includes several styles, such as jazz, rock, pop, blues, or music for cinema. We apply three consecutive tokenization/encoding strategies: 1) All chords are treated as unique elements. 2) Chords dynamically formatted as a tuple describing roots, nature, extensions, and slash chords. 3) An extension of model 2 with a style token and extension of the positional embedding layer of the transformer architecture. We analyze sequences generated by comparing them with the training dataset using trigram, which reveals common chord progressions and source duplications. We compare the generated sequences from a musical perspective, rating their plausibility in regard to the training data. The third strategy reported lower validation loss and better musical consistency in the suggested progressions.
Fichier principal
Vignette du fichier
Paper_template_for_ISMIR_LBD-1.pdf (1.37 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Licence : CC BY - Paternité

Dates et versions

hal-04289026 , version 1 (16-11-2023)

Licence

Paternité

Identifiants

  • HAL Id : hal-04289026 , version 1

Citer

David Dalmazzo, Ken Déguernel, Bob L. T. Sturm. The Chordinator: Chord progression modeling and generation using transformers. International Society for Music Information Retrieval Conference, 2023. ⟨hal-04289026⟩
77 Consultations
78 Téléchargements

Partager

Gmail Facebook X LinkedIn More