Abstract: We present and evaluate an application of affective adaptive generative music in a single-player, action-RPG video game. We create
a score that serves as an audience to the gameplay, based on the output of PreGLAM, which models the emotional perception of a game audience. We use the Multi-track Music Machine to expand and extend a composed adaptive musical score, and we use industry-standard production techniques to synthesize and perform all of
our musical scores.We evaluate our application of generative music in comparison to two composed scores, one adaptive and one linear. Our generative score is rated as nearly equivalent to a composed linear score in perceptions of emotional congruency, immersion, and preference.
“Pre-GLAM-MMM” presents an application of the “Multi-track Music Machine” (MMM) Music Transformer model in video games. PreGLAM-MMM uses the PreGLAM game emotion model to control the adaptivity of a musical score in 3 simultaneous emotional dimensions – Valence (pleasure/pleasantness), Arousal, and Tension.
PreGLAM-MMM uses a co-creative approach to the generative score. Our 3-dimensional adaptive score was composed following the findings of the IsoVAT composition guide in addition to standard adaptive music composition techniques. Our composed score consists of a single highly-adaptive 8-bar phrase, with 27 variations. We use standard game industry adaptive techniques to expand these 27 variations to 343 variations. We then use MMM’s generative music capabilities to expand this score into almost 14 trillion unique variations.
PreGLAM-MMM leverages the strengths of human composition and game design, alongside the strengths of computational creativity and generative music, to create a score that provides more musical adaptivity than seen in contemporary games, without reducing the amount of music.