Beat-Aligned Spectrogram-to-Sequence Generation of Rhythm-Game Charts
This addresses chart generation for rhythm games, which is an incremental improvement in a niche domain.
The paper tackles the problem of generating rhythm-game charts by formulating it as a sequence generation task and training a Transformer with tempo-informed preprocessing, achieving outperformance over baselines on a large dataset and benefits from pretraining and finetuning.
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.