AffectMachine-Pop: A controllable expert system for real-time pop music generation

2025-06-09

AI Summary

This study addresses three key challenges in pop music generation: weak emotional controllability, poor real-time performance, and lack of interpretability. We propose the first controllable, interpretable, low-latency expert system for pop music generation grounded in continuous affective dimensions—arousal and valence. Methodologically, it integrates music-theoretic rule modeling, an emotion–music mapping engine, real-time physiological interfaces (HRV/EEG), and a lightweight scheduling framework, enabling both preset-emotion-driven generation and closed-loop biophysiological feedback regulation. Contributions include: (1) the first explicit, human-interpretable, and editable mapping from the arousal–valence space to retro-style pop music; (2) end-to-end latency under 300 ms; (3) statistically significant emotional alignment in listening experiments (p < 0.01) with a mean opinion score (MOS) of 4.2/5; and (4) successful integration into a neurofeedback prototype, demonstrating practical utility in interactive affective composition and emotion regulation.

Technology Category

• Cognitive Modeling & Cognitive Systems: Affective Computing
• Natural Language Processing: Generation
• Humans and AI: Game Design — Procedural Content Generation & Storytelling

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications

Abstract

Music is a powerful medium for influencing listeners' emotional states, and this capacity has driven a surge of research interest in AI-based affective music generation in recent years. Many existing systems, however, are a black box which are not directly controllable, thus making these systems less flexible and adaptive to users. We present extit{AffectMachine-Pop}, an expert system capable of generating retro-pop music according to arousal and valence values, which can either be pre-determined or based on a listener's real-time emotion states. To validate the efficacy of the system, we conducted a listening study demonstrating that AffectMachine-Pop is capable of generating affective music at target levels of arousal and valence. The system is tailored for use either as a tool for generating interactive affective music based on user input, or for incorporation into biofeedback or neurofeedback systems to assist users with emotion self-regulation.

Problem

• Generates pop music based on emotional states
• Provides controllable AI music generation system
• Validates system efficacy through listening study

Innovation

• Expert system for real-time pop music generation
• Controllable via arousal and valence values
• Supports interactive and biofeedback applications