Vocal interaction fields reveal how people share emotions together
Shifting Relational Paradigms for Affective Computing: Affective Resonance, Vitality Affects, and Vocal Interaction Fields
Artificial Intelligence
Summary
Most systems that try to read emotions from speech focus only on one person at a time. The authors suggest this approach misses how emotions happen between people during conversations. They studied how voices in a group interact with each other very quickly, showing that emotions flow in a shared space, not just inside individuals. Their findings offer new ways to design technology that understands feelings by looking at these voice interactions.
What this means in practice
- •For conversational ai developers: Design AI systems that detect emotional interactions by analyzing fast voice exchanges between multiple speakers in conversations.$Commercial implications: Enables emotionally aware AI assistants that better respond to group dynamics and improve user engagement across calls or meetings.
- •For human communication trainers: Use measures of vocal coupling to assess and improve emotional connection skills in team communication or therapy training.
Authors
Cy Gorman, Yihang Yao
Abstract
Affective computing has largely followed an individual-state paradigm, extracting discrete emotion labels or arousal/valence from isolated speakers. We argue this framing is incomplete for interaction. Drawing on affective resonance and vitality-contour accounts, we propose a relational framework in which the primary unit of affective analysis is the interactional field constituted within vocal dynamics. As a proof of concept, we present a preliminary empirical study using continuous self-supervised speech representations to detect directional expressive coupling in multi-party conversation. Coupling is regime-specific, concentrated at sub-second timescales, and collapses under exclusive-speech negative controls, consistent with a relational account of affective dynamics. We introduce design frameworks for Artificial Affective Resonance Intelligence grounded in Affective Resonance Dynamic Ontologies, supported by null-calibrated directional coupling analyses across interaction regimes.