arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~

ITGPT:一种基于Transformer的用于生成《劲舞革命》和《狂热节拍》谱面的架构

ITGPT: A Transformer Based Architecture for the Generation of Dance Dance Revolution and In the Groove Charts

Miguel O'Malley

arXiv 2607.14148首次发表:更新:

AI 中文总结

研究针对《劲舞革命》和《狂热节拍》谱面生成难题,提出基于Transformer的ITGPT架构,相比前人工作,该架构在生成准确性和计算成本上有显著提升。

AI 中文摘要

《劲舞革命》和《狂热节拍》是由歌曲及配套编排(即谱面)组成的节奏游戏。玩家需在舞毯设备上按照歌曲谱面确定的舞步及时按下箭头。手动生成谱面耗时且困难,激发了对自动化的兴趣。我们提出了ITGPT,一种用于生成DDR/ITG谱面的新型基于Transformer的架构,并证明与之前的工作相比,在生成准确性和计算成本方面有显著改进。

英文摘要

Dance Dance Revolution and In the Groove are rhythm games consisting of songs and accompanying choreography, referred to as charts. Players press arrows on a device referred to as a dance pad in time with steps determined by the song's chart. The process of manual chart generation is timestaking and difficult, motivating interest in automation. We propose ITGPT, a new transformer based architecture for the generation of DDR/ITG charts, and demonstrate significant improvements to generation accuracy and computational cost in comparison to predecessor work.

Comments14 pages, 11 figures, 2 tables + appendix

论文原文

arXiv 摘要页 · PDF 原文 · HTML 原文

↑