Proceedings of the Annual Conference of JSAI
Online ISSN : 2758-7347
34th (2020)
Session ID : 4C2-GS-13-04
Conference information

Game BGM Selection System Based on Scenario and Emotional State
*Takuma YAMAUCHISakura NEMOTOKyosuke NAGANOShogo NAKAMURAYuuri SAITOAkiko UDAHajime MURAIKazushi MUKAIYAMAEmiko TAYANAGIKeiji HIRATA
Author information
CONFERENCE PROCEEDINGS FREE ACCESS

Details
Abstract

In this paper, we describe a system for automatically selecting BGM for a given game scene. This system is supposed to function as a part of the automatic RPG generation system. When an automatically generated game scenario is input, BGM that matches the emotional state of each game scene is selected from a database. When the emotional state of the scene specified in the game scenario is given to a neural network, the corresponding acoustic features are calculated, and a musical piece with similar acoustic features is selected from the BGM candidate database. Currently, the whole operation has been confirmed by incorporating the BGM selection module presented here into an automatic RPG generation system, and the preparations for subject experiments are underway.

Content from these authors
© 2020 The Japanese Society for Artificial Intelligence
Previous article Next article
feedback
Top