In conversation, humans use multimodal cues, such as speech, gestures, and gaze, to manage turn-taking. While linguistic and acoustic features are informative, gestures provide complementary cues for modeling these transitions. To study this, we introduce DnD Gesture++, an extension of the multi-party DnD Gesture corpus enriched with 2,663 semantic gesture annotations spanning iconic, metaphoric, deictic, and discourse types. Using this dataset, we model turn-taking prediction through a Mixture-of-Experts framework integrating text, audio, and gestures. Experiments show that incorporating semantically guided gestures yields consistent performance gains over baselines, demonstrating their complementary role in multimodal turn-taking.
@article{arxiv.2510.19350,
title = {Modeling Turn-Taking with Semantically Informed Gestures},
author = {Varsha Suresh and M. Hamza Mughal and Christian Theobalt and Vera Demberg},
journal= {arXiv preprint arXiv:2510.19350},
year = {2026}
}