19 papers
Does Listening Matter? Backchanneling and Nodding in AI Clone
Koji Inoue, Kazushi Kato, Tatsuya Kawahara +1
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 be…
Low-Latency Turn-Taking via Context-Aware Preface Generation in a Real-World Dialogue Robot
Yuki Okafuji, Koji Inoue, Yoshiki Ohira
Large language model (LLM)-based dialogue systems suffer response delays because generation begins only after final speech recognition. While fixed fillers are a workaround, they b…
On the Structure of Address in Multi-Party Dialogue: From Discrete Labels to Continuous Levels
Taiga Mori, Koji Inoue, Divesh Lala +1
In multi-party dialogues between a dialogue system and multiple users, identifying to whom an utterance is addressed is a key challenge. Prior work has typically treated addressee…
Memory-Driven Self-Disclosure and Relational Turning Points: A Longitudinal Multimodal Study of Human-AI Interaction
Ryuichi Sumida, Mao Saeki, Masaki Eguchi +4
The paper reports a longitudinal study of a memory‑augmented conversational AI, showing how perceived memory and self‑disclosure shape user enjoyment over repeated sessions and how…
Real-time Generation of Listener Nodding via Prediction of Kinematic Parameters for Avatar Dialogue Systems
Kazushi Kato, Koji Inoue, Taiga Mori +2
The paper introduces a lightweight, real-time model that predicts both the timing and motion parameters of listener nodding for conversational avatars, using a dyadic attention net…
I Understand How You Feel: Enhancing Deeper Emotional Support Through Multilingual Emotional Validation in Dialogue System
Zi Haur Pang, Yahui Fu, Koji Inoue +1
Emotional validation - explicitly acknowledging that a user's feelings make sense - has proven therapeutic value but has received little computational attention. Emotional validati…