preprint · arXiv (2026) · Jan 29, 2026
Auditorily Embodied Conversational Agents: Effects of Spatialization and Situated Audio Cues on Presence and Social Perception
Yi Fei Cheng, Andrea Bianchi, Jarod Bloch, Anusha Withana, Alexander Wang, Anhong Guo, Laurie M. Heller, David Lindlbauer
In plain English
You can give an agent a body using sound alone — placing its voice in space and adding background noises of it doing things — and 24 participants did feel it was more present in the room with them. But the same cues made the agent seem less attentive, less likeable and less socially attractive, and people said about 20 fewer words per conversation. If you are building a voice-first agent, spatial audio buys presence, but incidental sound effects read as the agent being distracted, which is a poor trade in any service or coaching context. Accepted to ACM CHI 2026.
Abstract
Embodiment can enhance conversational agents, such as increasing their perceived presence. This is typically achieved through visual representations of a virtual body; however, visual modalities are not always available, such as when users interact with agents using headphones or display-less glasses. In this work, we explore auditory embodiment. By introducing auditory cues of bodily presence - through spatially localized voice and situated Foley audio from environmental interactions - we investigate how audio alone can convey embodiment and influence perceptions of a conversational agent. We conducted a 2 (spatialization: monaural vs. spatialized) x 2 (Foley: none vs. Foley) within-subjects study, where participants (n=24) engaged in conversations with agents. Our results show that spatialization and Foley increase co-presence, but reduce users' perceptions of the agent's attention and other social attributes.
Related research
- Effects of AI-Powered Embodied Avatars on Communication Quality and Social Connection in Asynchronous Virtual Meetings
- TANDE: Disentangling Verbal and Nonverbal Backchannels in Emotional AI-Avatar Conversations with Young Adults
- Listening and Mirroring: The Effects of Verbal Attunement and Behavioral Mimicry on Social and Empathic Perceptions of Embodied AI Agents in VR