Expressive Auditory Gestures in a Voice-Based Pedagogical Agent
Jessy Ceha, Edith Law
Abstract
In this paper, we explore how expressive auditory gestures added to the speech of a pedagogical agent influence the human-agent relationship and learning outcomes. In a between-subjects experiment, 41 participants assumed the role of a tutor to teach a voice-based agent. The agent used either: expressive interjections (e.g.,“yay”, “hmm”, “oh”), brief expressive musical executions, or no auditory gestures at all (control condition), throughout the interaction. Overall, the results indicate that both gestures can positively affect the interaction, but in particular, interjections can significantly increase feelings of emotional rapport with the agent and enhance motivation in learners. The implications of our findings are discussed as our work adds to the understanding of conversational agent design and can be useful for education as well as other domains in which dialogue systems are used.
Ask about this paper
Ask your agent about it.
Lune has read the top-tier papers around this one, so every answer names the papers it rests on.
Your agent calls
Lunesearch_papers
Free to start. No credit card required.
Terminal
Install the CLIlune papers get 60200e7a-957d-4a85-abaf-308b12a6761cCited by top-tier papers1
Ask how each one uses itRelated papers
- "You might think about slightly revising the title": Identifying Hedges in Peer-tutoring InteractionsYann Raphalen, Chloé Clavel, Justine CassellACL 2022 · 14 citations
- Who You Explain To Matters: Learning by Explaining to Conversational Agents with Different Pedagogical RolesZhengtao Xu, Junti Zhang, Anthony Tang, Yi-Chieh LeeCHI 2026 · 2 citations
- Should Voice Agents Be Polite in an Emergency? Investigating Effects of Speech Style and Voice Tone in Emergency SimulationJieun Kim, Susan R. FussellCHI 2025 · 10 citations
- 'Show It, Don't Just Say It': The Complementary Effects of Instruction Multimodality for Software GuidanceEmran Poh, Yueyue Hou, Tianyi Zhang, Jiannan LiCHI 2026 · 1 citation
- Text2Gestures: A Transformer-Based Network for Generating Emotive Body Gestures for Virtual Agents**This work has been supported in part by ARO Grants W911NF1910069 and W911NF1910315, and Intel. Code and additional materials available at: https: //gamma.umd.edu/t2gUttaran Bhattacharya, Nicholas Rewkowski, Abhishek Banerjee, Pooja Guhan et al.IEEE VR 2021 · 147 citations
