Year: 2025
Type: article
Abstract: As artificial intelligence (AI) systems become increasingly integrated into human social environments, their ability to foster meaningful interaction remains an open challenge. Building on research showing that physiological synchrony relates to social bonding, we speculate about an interpersonal musical biofeedback system that promotes synchrony by allowing users to attune to each other’s physiological rhythms. We propose a two‑stage AI training framework for an interpersonal musical biofeedback system: (1) a Foundational Model trained on diverse listeners’ physiological responses to a music library, and (2) Individualized Tuning, where the system fine-tunes itself to each user’s unique physiological responses. By analyzing musical features alongside real-time physiological responses, the proposed system illustrates a feasible architecture for dynamically personalizing music to facilitate nonverbal, embodied communication between users. This approach highlights the potential for AI-driven personalization that move beyond individual optimization to actively enhance physiological synchrony which may promote deeper emotional bonding and expand the role of music as a medium for AI-mediated social connections.
Source: Frontiers in Computer Science
Authors: Senaida Ng, Kaia Sargent, Jason J. Snell
Institutions: New York University, University of California, Los Angeles
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $1,418
OpenAlex ID: W4413961382