Does Listening Matter? Backchanneling and Nodding in AI Clone

2026-08-19

AI Summary

研究通过在AI克隆中加入实时预测模型驱动的口头反馈和点头行为，提高了其互动倾听行为的真实性和存在感。

Abstract

AI clones that imitate a specific person typically reproduce what the person says and how they sound, but not how they listen. We investigate whether adding multimodal listening behaviors gives such a clone more presence and authenticity. We integrated verbal backchannels and head nodding, driven by real-time prediction models, into an AI clone equipped with voice cloning and LLM-based responses. In a within-subjects study (N=35), adding these behaviors significantly improved the perceived attentiveness of the avatar, the sense of talking with the real person, and the feeling of co-presence. These results indicate that AI clone fidelity should extend beyond voice and response content to include interactive listening behavior.

Problem

• AI clone
• listening behavior
• presence
• authenticity
• backchanneling

Innovation

• multimodal listening behaviors
• backchannels
• head nodding
• real-time prediction models