Computer-Generated Music for Tabletop Role-Playing Games

TL;DR

This paper introduces Bardo Composer, a system that generates emotionally appropriate background music for tabletop role-playing games using speech recognition, emotion classification, and a novel stochastic search method, validated by user studies.

Contribution

The paper presents a novel system combining speech recognition, emotion modeling, and a new stochastic search algorithm to generate expressive game music.

Findings

Participants correctly identified emotions in generated music as well as human-composed pieces.

Bardo Composer effectively translates player speech into emotionally relevant music.

The system demonstrates potential for enhancing immersive gameplay experiences.

Abstract

In this paper we present Bardo Composer, a system to generate background music for tabletop role-playing games. Bardo Composer uses a speech recognition system to translate player speech into text, which is classified according to a model of emotion. Bardo Composer then uses Stochastic Bi-Objective Beam Search, a variant of Stochastic Beam Search that we introduce in this paper, with a neural model to generate musical pieces conveying the desired emotion. We performed a user study with 116 participants to evaluate whether people are able to correctly identify the emotion conveyed in the pieces generated by the system. In our study we used pieces generated for Call of the Wild, a Dungeons and Dragons campaign available on YouTube. Our results show that human subjects could correctly identify the emotion of the generated music pieces as accurately as they were able to identify the emotion of pieces written by humans.