%0 Conference Proceedings
%T Dance Dance Gradation: A Generation of Fine-Tuned Dance Charts
%+ Ritsumeikan University
%A Tsujino, Yudai
%A Yamanishi, Ryosuke
%Z Part 1: Full Papers
%< avec comité de lecture
%( Lecture Notes in Computer Science
%B 17th International Conference on Entertainment Computing (ICEC)
%C Poznan, Poland
%Y Esteban Clua
%Y Licinio Roque
%Y Artur Lugmayr
%Y Pauliina Tuomi
%I Springer International Publishing
%3 Entertainment Computing – ICEC 2018
%V LNCS-11112
%P 175-187
%8 2018-09-17
%D 2018
%R 10.1007/978-3-319-99426-0_15
%K Rhythm-based video games
%K Procedural content generation
%K Difficulty Adjustment
%Z Computer Science [cs]Conference papers
%X This paper proposes a system to automatically generate dance charts with fine-tuned difficulty levels: Dance Dance Gradation (DDG). The system learns the relationships between difficult and easy charts based on the deep neural network using a dataset of dance charts with different difficulty levels as the training data. The difficulty chart automatically would be adapted to easier charts through the learned model. As mixing multiple difficulty levels for the training data, the generated charts should have each characteristic of difficulty level. The user can obtain the charts with intermediate difficulty level between two different levels. Through the objective evaluation and the discussions for the output results, it was suggested that the proposed system generated the charts with each characteristic of the difficulty level in the training dataset.
%G English
%Z TC 14
%Z WG 14.4
%2 https://inria.hal.science/hal-02128628/document
%2 https://inria.hal.science/hal-02128628/file/472623_1_En_15_Chapter.pdf
%L hal-02128628
%U https://inria.hal.science/hal-02128628
%~ IFIP-LNCS
%~ IFIP
%~ IFIP-WG
%~ IFIP-ICEC
%~ IFIP-TC14
%~ IFIP-LNCS-11112
%~ IFIP-WG14-4