arXiv Open Access 2022

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

Gustavo Amaral Costa dos Santos Augusto Baffa Jean-Pierre Briot Bruno Feijó Antonio Luz Furtado

Lihat Sumber

Abstrak

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.

Topik & Kata Kunci

cs.SD cs.LG cs.MM eess.AS

Penulis (5)

Gustavo Amaral Costa dos Santos

Augusto Baffa

Jean-Pierre Briot

Bruno Feijó

Antonio Luz Furtado

Format Sitasi

APA MLA BibTeX

Santos, G.A.C.d., Baffa, A., Briot, J., Feijó, B., Furtado, A.L. (2022). An adaptive music generation architecture for games based on the deep learning Transformer mode. https://arxiv.org/abs/2207.01698

Akses Cepat

Lihat di Sumber

Informasi Jurnal

Tahun Terbit: 2022
Bahasa: en
Sumber Database: arXiv
Akses: Open Access ✓