Adaptive Music Composition for Games

Abstract

The generation of music that adapts dynamically to content and actions has an important role in building more immersive, memorable and emotive game experiences. To date, the development of adaptive music systems for video games is limited by both the nature of algorithms used for real-time music generation and the limited modelling of player action, game world context and emotion in current games. We propose that these issues must be addressed in tandem for the quality and flexibility of adaptive game music to significantly improve. Cognitive models of knowledge organisation and emotional affect are integrated with multi-modal, multi-agent composition techniques to produce a novel Adaptive Music System (AMS). The system is integrated into two stylistically distinct games. Gamers reported an overall higher immersion and correlation of music with game-world concepts with the AMS than with the original game soundtracks in both games.

An adaptive music generation architecture for games based on the deep learning Transformer model

“…The only surveyed game music generation system based on artificial neural networks is Adaptive Music System (AMS) by Hutchings and McCormack [8] and it will be summarized in next section (Section II-B). Generative music is more general and adaptive than precomposed composed adaptive music, but is also more difficult to control and more computing demanding.…”

“…Activation spreads as a function of the number of mediating edges and their weights. As explained in [8]: "Spreading activation models don't require logical structuring of concepts into classes or defining features, making it possible to add content based on context rather than structure. For example, if a player builds a house out of blocks in Minecraft, it does not need to be identified as a house.…”

“…In this context, instead of looking for alternatives or improvements in the few existing complete models for game music generation (such as the excellent work by Hutchings and McCormack [8], to be analyzed in Section II-B), we decided to explore more straightforward and flexible models for generating and adapting music, based on layering [7]. Also, we believe that our proposed model can facilitate the control and orchestration of music for video games in a collaborative environment.…”

Procedural Content Generation through Quality Diversity

“…While the cases surveyed in Section IV focused mostly on the generation of levels and visuals, it is important to explore how QD algorithms can work with different facets of game content such as rules [50], music [51], etc. These facets come with their own challenges in defining quality or diversity.…”

Minimizing the Total Tardiness of a Game Project Considering the Overlap Effect

“…Similarly, we can let another experienced developer to process the jobs of modeling all the different civilians. For more research into game development, please refer to [28][29][30][31][32][33][34][35][36].…”