Beat-Aligned Spectrogram-to-Sequence Generation of Rhythm-Game Charts
Machine Learning
2023-11-27 v1 Multimedia
Sound
Audio and Speech Processing
Abstract
In the heart of "rhythm games" - games where players must perform actions in sync with a piece of music - are "charts", the directives to be given to players. We newly formulate chart generation as a sequence generation task and train a Transformer using a large dataset. We also introduce tempo-informed preprocessing and training procedures, some of which are suggested to be integral for a successful training. Our model is found to outperform the baselines on a large dataset, and is also found to benefit from pretraining and finetuning.
Cite
@article{arxiv.2311.13687,
title = {Beat-Aligned Spectrogram-to-Sequence Generation of Rhythm-Game Charts},
author = {Jayeon Yi and Sungho Lee and Kyogu Lee},
journal= {arXiv preprint arXiv:2311.13687},
year = {2023}
}
Comments
ISMIR 2023 LBD. Demo videos and code at stet-stet.github.io/goct