Papers
3
Total Citations
318
H-Index
3
About
Geehyuk Lee is a leading researcher at the intersection of human-robot interaction, artificial intelligence, and multimodal communication. His work focuses on enabling robots and virtual agents to communicate more naturally by generating human-like, co-speech gestures—the spontaneous hand and body movements that accompany speech. Lee’s major contribution is pioneering end-to-end deep learning models that allow robots to learn social skills directly from data, eliminating the need for labor-intensive, rule-based programming. His landmark 2020 paper, "Speech gesture generation from the trimodal context of text, audio, and speaker identity," has garnered over 300 citations, demonstrating its profound impact on the field. This work advanced the state of the art by integrating multiple input modalities to produce more expressive and contextually appropriate gestures. Through his research, Lee is fundamentally reshaping how we design social robots and virtual avatars, making them appear more alive and engaging in human-agent interaction. His contributions are essential reading for anyone interested in building the next generation of socially intelligent machines.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3