Research

Paper

AI LLM March 10, 2026

Reading the Mood Behind Words: Integrating Prosody-Derived Emotional Context into Socially Responsive VR Agents

Authors

SangYeop Jeong, Yeongseo Na, Seung Gyu Jeong, Jin-Woo Jeong, Seong-Eun Kim

Abstract

In VR interactions with embodied conversational agents, users' emotional intent is often conveyed more by how something is said than by what is said. However, most VR agent pipelines rely on speech-to-text processing, discarding prosodic cues and often producing emotionally incongruent responses despite correct semantics. We propose an emotion-context-aware VR interaction pipeline that treats vocal emotion as explicit dialogue context in an LLM-based conversational agent. A real-time speech emotion recognition model infers users' emotional states from prosody, and the resulting emotion labels are injected into the agent's dialogue context to shape response tone and style. Results from a within-subjects VR study (N=30) show significant improvements in dialogue quality, naturalness, engagement, rapport, and human-likeness, with 93.3% of participants preferring the emotion-aware agent.

Metadata

arXiv ID: 2603.09324
Provider: ARXIV
Primary Category: cs.HC
Published: 2026-03-10
Fetched: 2026-03-11 06:02

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.09324v1</id>\n    <title>Reading the Mood Behind Words: Integrating Prosody-Derived Emotional Context into Socially Responsive VR Agents</title>\n    <updated>2026-03-10T07:58:06Z</updated>\n    <link href='https://arxiv.org/abs/2603.09324v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.09324v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>In VR interactions with embodied conversational agents, users' emotional intent is often conveyed more by how something is said than by what is said. However, most VR agent pipelines rely on speech-to-text processing, discarding prosodic cues and often producing emotionally incongruent responses despite correct semantics. We propose an emotion-context-aware VR interaction pipeline that treats vocal emotion as explicit dialogue context in an LLM-based conversational agent. A real-time speech emotion recognition model infers users' emotional states from prosody, and the resulting emotion labels are injected into the agent's dialogue context to shape response tone and style. Results from a within-subjects VR study (N=30) show significant improvements in dialogue quality, naturalness, engagement, rapport, and human-likeness, with 93.3% of participants preferring the emotion-aware agent.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.HC'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n    <published>2026-03-10T07:58:06Z</published>\n    <arxiv:comment>12 pages, 4 figures, Accepted to CHI EA 2026 (Extended Abstracts of the 2026 CHI Conference on Human Factors in Computing Systems)</arxiv:comment>\n    <arxiv:primary_category term='cs.HC'/>\n    <arxiv:journal_ref>Extended Abstracts of the 2026 CHI Conference on Human Factors in Computing Systems (CHI EA '26), 2026, 1-12</arxiv:journal_ref>\n    <author>\n      <name>SangYeop Jeong</name>\n    </author>\n    <author>\n      <name>Yeongseo Na</name>\n    </author>\n    <author>\n      <name>Seung Gyu Jeong</name>\n    </author>\n    <author>\n      <name>Jin-Woo Jeong</name>\n    </author>\n    <author>\n      <name>Seong-Eun Kim</name>\n    </author>\n    <arxiv:doi>10.1145/3772363.3798643</arxiv:doi>\n    <link href='https://doi.org/10.1145/3772363.3798643' rel='related' title='doi'/>\n  </entry>"
}