GestureCoach: Rehearsing for Engaging Talks with LLM-Driven Gesture Recommendations
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914086490472448 |
|---|---|
| author | Ram, Ashwin Suresh, Varsha Abadian, Artin Saberpour Demberg, Vera Steimle, Jürgen |
| author_facet | Ram, Ashwin Suresh, Varsha Abadian, Artin Saberpour Demberg, Vera Steimle, Jürgen |
| contents | This paper introduces GestureCoach, a system designed to help speakers deliver more engaging talks by guiding them to gesture effectively during rehearsal. GestureCoach combines an LLM-driven gesture recommendation model with a rehearsal interface that proactively cues speakers to gesture appropriately. Trained on experts' gesturing patterns from TED talks, the model consists of two modules: an emphasis proposal module, which predicts when to gesture by identifying gesture-worthy text segments in the presenter notes, and a gesture identification module, which determines what gesture to use by retrieving semantically appropriate gestures from a curated gesture database. Results of a model performance evaluation and user study (N=30) show that the emphasis proposal module outperforms off-the-shelf LLMs in identifying suitable gesture regions, and that participants rated the majority of these predicted regions and their corresponding gestures as highly appropriate. A subsequent user study (N=10) showed that rehearsing with GestureCoach encouraged speakers to gesture and significantly increased gesture diversity, resulting in more engaging talks. We conclude with design implications for future AI-driven rehearsal systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_10706 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | GestureCoach: Rehearsing for Engaging Talks with LLM-Driven Gesture Recommendations Ram, Ashwin Suresh, Varsha Abadian, Artin Saberpour Demberg, Vera Steimle, Jürgen Human-Computer Interaction This paper introduces GestureCoach, a system designed to help speakers deliver more engaging talks by guiding them to gesture effectively during rehearsal. GestureCoach combines an LLM-driven gesture recommendation model with a rehearsal interface that proactively cues speakers to gesture appropriately. Trained on experts' gesturing patterns from TED talks, the model consists of two modules: an emphasis proposal module, which predicts when to gesture by identifying gesture-worthy text segments in the presenter notes, and a gesture identification module, which determines what gesture to use by retrieving semantically appropriate gestures from a curated gesture database. Results of a model performance evaluation and user study (N=30) show that the emphasis proposal module outperforms off-the-shelf LLMs in identifying suitable gesture regions, and that participants rated the majority of these predicted regions and their corresponding gestures as highly appropriate. A subsequent user study (N=10) showed that rehearsing with GestureCoach encouraged speakers to gesture and significantly increased gesture diversity, resulting in more engaging talks. We conclude with design implications for future AI-driven rehearsal systems. |
| title | GestureCoach: Rehearsing for Engaging Talks with LLM-Driven Gesture Recommendations |
| topic | Human-Computer Interaction |
| url | https://arxiv.org/abs/2504.10706 |