Procedural Content Generation of Rhythm Games Using Deep Learning Methods - Entertainment Computing and Serious Games Access content directly
Conference Papers Year : 2019

Procedural Content Generation of Rhythm Games Using Deep Learning Methods

Yubin Liang
  • Function : Author
  • PersonId : 1133221
Wanxiang Li
  • Function : Author
  • PersonId : 1133222
Kokolo Ikeda
  • Function : Author
  • PersonId : 1031175

Abstract

The rhythm game is a type of video game which is popular to many people. But the game contents (required action and its timing) of rhythm game are usually hand-crafted by human designers. In this research, we proposed an automatic generation method to generate game contents from the music file of the famous rhythm game “OSU!” 4k mode. Generally, the supervised learning method is used to generate such game contents. In this research some new methods are purposed, one is called “fuzzy label” method, which shows better performance on our training data. Another is to use the new model C-BLSTM. On our test data, we improved the F-Score of timestamp prediction from 0.8159 to 0.8430. Also, it was confirmed through experiments that human players could feel the generated beatmap is more natural than previous research.
Fichier principal
Vignette du fichier
491829_1_En_11_Chapter.pdf (1.2 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03652042 , version 1 (26-04-2022)

Licence

Attribution

Identifiers

Cite

Yubin Liang, Wanxiang Li, Kokolo Ikeda. Procedural Content Generation of Rhythm Games Using Deep Learning Methods. 1st Joint International Conference on Entertainment Computing and Serious Games (ICEC-JCSG), Nov 2019, Arequipa, Peru. pp.134-145, ⟨10.1007/978-3-030-34644-7_11⟩. ⟨hal-03652042⟩
112 View
606 Download

Altmetric

Share

Gmail Facebook X LinkedIn More