Titre :

ChromaFlow: Modeling And Generating Harmonic Progressions With a Transformer And Voicing Encoding

Auteur(s) :

Dalmazzo, David [Auteur]
KTH Royal Institute of Technology [Stockholm] [KTH]
Deguernel, Ken [Auteur]
Centre National de la Recherche Scientifique [CNRS]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Sturm, Bob [Auteur]
KTH Royal Institute of Technology [Stockholm] [KTH]

Titre de la manifestation scientifique :

MML 2024: ​15th International Workshop on Machine Learning and Music

Ville :

Vilnius

Pays :

Lituanie

Date de début de la manifestation scientifique :

2024

Titre de l’ouvrage :

Proceedings of the 15th International Workshop on Machine Learning and Music (MML 2024)

Mot(s)-clé(s) en anglais :

Music Generation
Chord Progressions
The Transformer Network

Discipline(s) HAL :

Informatique [cs]/Intelligence artificielle [cs.AI]
Sciences de l'Homme et Société/Musique, musicologie et arts de la scène

Résumé en anglais : [en]

Modeling harmonic progressions in symbolic music is a complex task that requires generating musically coherent and varied chord sequences. In this study, we employ a transformer-based architecture trained on a comprehensive ...
Lire la suite >Modeling harmonic progressions in symbolic music is a complex task that requires generating musically coherent and varied chord sequences. In this study, we employ a transformer-based architecture trained on a comprehensive dataset of 48,072 songs, which includes an augmented set of 4,300 original pieces from the iReal Pro application transposed across all chromatic keys. We introduce a novel tokenization and voicing encoding strategy designed to enhance the musicality of the generated chord progressions. Our approach not only generates chord progression suggestions but also provides corresponding voicings tailored for instruments such as piano and guitar. To evaluate the effectiveness of our model, we conducted a listening test comparing the harmonic progressions produced by our approach against those from a baseline model. The results indicate that our model generates progressions with more fluid voicings, coherent harmonic motion, and plausible chord suggestions, effectively utilizing repetition and variation to enhance musicality.Lire moins >

Langue :

Anglais

Comité de lecture :

Oui

Audience :

Internationale

Vulgarisation :

Non

Projet Européen :

ERC-2019-COG No. 864189 MUSAiC: Music at the Frontiers of Artificial Creativity and Criticism

Collections :

• Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189

Source :

Harvested from HAL