Gen\'eLive! Generating Rhythm Actions in Love Live!

TL;DR

This paper introduces GenéLive!, a deep generative model for rhythm game chart creation that leverages musical structures, outperforming previous models and significantly reducing production costs for a popular franchise.

Contribution

The paper presents GenéLive!, a novel generative model that incorporates musical beats and scales, improving rhythm chart generation and operational efficiency in the industry.

Findings

GenéLive! outperforms state-of-the-art models in chart generation quality.

Implementation of GenéLive! reduced business costs by up to 50%.

Model is publicly available and validated on real production datasets.

Abstract

This article presents our generative model for rhythm action games together with applications in business operations. Rhythm action games are video games in which the player is challenged to issue commands at the right timings during a music session. The timings are rendered in the chart, which consists of visual symbols, called notes, flying through the screen. We introduce our deep generative model, Gen\'eLive!, which outperforms the state-of-the-art model by taking into account musical structures through beats and temporal scales. Thanks to its favorable performance, Gen\'eLive! was put into operation at KLab Inc., a Japan-based video game developer, and reduced the business cost of chart generation by as much as half. The application target included the phenomenal "Love Live!," which has more than 10 million users across Asia and beyond, and is one of the few rhythm action franchises that has led the online era of the genre. In this article, we evaluate the generative performance of Gen\'eLive! using production datasets at KLab as well as open datasets for reproducibility, while the model continues to operate in their business. Our code and the model, tuned and trained using a supercomputer, are publicly available.