DialoGen: Towards Dialog Gesture Generation via Identity-Decoupled Style Guidance in Interactive Diffusion Model
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (16) · 13253-13261
DOI: 10.1609/aaai.v40i16.38327 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Weiyu Zhao und 5 weiteren Autor:innen.
Abstract (Originalsprache)
We propose DialoGen, a novel framework for generating realistic gestures for both interlocutors in dialog scenarios, conditioned on conversational audios. Unlike most existing methods that focus solely on a single speaker, DialoGen simultaneously generates synchronized gestures for both participants while also embedding identity-decoupled style into generated gestures that enhance realism and expressiveness. To ensure precise synchronization between interlocutors, DialoGen adopts an interactive dual-diffusion model with mutual interaction estimation, which integrates interaction correlation into the diffusion process. More importantly, by leveraging supervised contrastive learning, we develop the identity-decoupled style guidance to adaptively decompose the identity-specific style of interlocutors into latent space, enabling multi-style dialog gesture generation. Extensive experimental results demonstrate that our model significantly outperforms existing methods in generating realistic, speech-aligned, identity-specific gestures, offering a high-quality solution for various dialog scenarios.
Zitieren
APA
Zhao, W., Wang, C., Hu, L., Li, Z., Yu, W., & Zhang, S. (2026). DialoGen: Towards Dialog Gesture Generation via Identity-Decoupled Style Guidance in Interactive Diffusion Model. Proceedings of the AAAI Conference on Artificial Intelligence, 40(16), 13253-13261. https://doi.org/10.1609/aaai.v40i16.38327
Vancouver
Zhao W, Wang C, Hu L, Li Z, Yu W, Zhang S. DialoGen: Towards Dialog Gesture Generation via Identity-Decoupled Style Guidance in Interactive Diffusion Model. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(16):13253-13261. doi:10.1609/aaai.v40i16.38327
BibTeX
@article{Zhao2026,
author = {Zhao, Weiyu and Wang, Chenyang and Hu, Liangxiao and Li, Zonglin and Yu, Wei and Zhang, Shengping},
title = {DialoGen: Towards Dialog Gesture Generation via Identity-Decoupled Style Guidance in Interactive Diffusion Model},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {16},
pages = {13253--13261},
doi = {10.1609/aaai.v40i16.38327}
}
EUVIMED