Context-Aware Emotionally Adaptive Voice Assistants: A Multimodal Framework for Empathetic Human-Agent Interaction
2.60T1 sourcearXiv cs.HC
Source record
Published by arXiv cs.HC (T1 source). The original is at https://arxiv.org/abs/2609.16417.
Pipeline notes
The summary and note below are generated by the signal pipeline — they are Beyond Desk’s reading, not quotations from the source.
SummaryPaper presents EmpathicVA, a closed-loop framework for voice assistants that integrates physiological sensing (HRA, EDA, respiration), vocal-affect analysis, contextual cues, and a Double DQN to decide when and how to interrupt. A 6-week study with 48 participants reported higher satisfaction, trust, and timing appropriateness, with reduced interruption-related stress.
Why it mattersA field study with physiological sensors showing affect-aware interruption policy outperforms context-only baselines on stress and timing metrics — useful evidence for anyone designing agent interruption behavior.
Cited by
No citations on record.