Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Suresh, Varsha, Mughal, M. Hamza, Theobalt, Christian, Demberg, Vera
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2510.19350
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917353837559808
author Suresh, Varsha
Mughal, M. Hamza
Theobalt, Christian
Demberg, Vera
author_facet Suresh, Varsha
Mughal, M. Hamza
Theobalt, Christian
Demberg, Vera
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_19350
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Modeling Turn-Taking with Semantically Informed Gestures
Suresh, Varsha
Mughal, M. Hamza
Theobalt, Christian
Demberg, Vera
Computation and Language
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.
title Modeling Turn-Taking with Semantically Informed Gestures
topic Computation and Language
url https://arxiv.org/abs/2510.19350