An adaptive music generation architecture for games based on the deep learning Transformer model - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

An adaptive music generation architecture for games based on the deep learning Transformer model

Résumé

This paper presents an architecture for generating music for video games based on the Transformer deep learning model. Our motivation is to be able to customize the generation according to the taste of the player, who can select a corpus of training examples, corresponding to his preferred musical style. The system generates various musical layers, following the standard layering strategy currently used by composers designing video game music. To adapt the music generated to the game play and to the player(s) situation, we are using an arousal-valence model of emotions, in order to control the selection of musical layers. We discuss current limitations and prospects for the future, such as collaborative and interactive control of the musical components.
Fichier principal
Vignette du fichier
music-games-sbgames-2022.pdf (275.54 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03787491 , version 1 (30-09-2022)

Identifiants

Citer

Gustavo Amaral, Augusto Baffa, Jean-Pierre Briot, Bruno Feijó, Antonio Furtado. An adaptive music generation architecture for games based on the deep learning Transformer model. 21st Brazilian Symposium on Computer Games and Digital Entertainment (SBGames), Oct 2022, Natal, Brazil. pp.1-6, ⟨10.1109/SBGAMES56371.2022.9961081⟩. ⟨hal-03787491⟩
40 Consultations
174 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More