SARGes: Semantically Aligned Reliable Gesture Generation via Intent Chain

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gao, Nan, Bao, Yihua, Weng, Dongdong, Zhao, Jiayi, Li, Jia, Zhou, Yan, Wan, Pengfei, Zhang, Di
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915213763149824
author Gao, Nan
Bao, Yihua
Weng, Dongdong
Zhao, Jiayi
Li, Jia
Zhou, Yan
Wan, Pengfei
Zhang, Di
author_facet Gao, Nan
Bao, Yihua
Weng, Dongdong
Zhao, Jiayi
Li, Jia
Zhou, Yan
Wan, Pengfei
Zhang, Di
contents Co-speech gesture generation enhances human-computer interaction realism through speech-synchronized gesture synthesis. However, generating semantically meaningful gestures remains a challenging problem. We propose SARGes, a novel framework that leverages large language models (LLMs) to parse speech content and generate reliable semantic gesture labels, which subsequently guide the synthesis of meaningful co-speech gestures.First, we constructed a comprehensive co-speech gesture ethogram and developed an LLM-based intent chain reasoning mechanism that systematically parses and decomposes gesture semantics into structured inference steps following ethogram criteria, effectively guiding LLMs to generate context-aware gesture labels. Subsequently, we constructed an intent chain-annotated text-to-gesture label dataset and trained a lightweight gesture label generation model, which then guides the generation of credible and semantically coherent co-speech gestures. Experimental results demonstrate that SARGes achieves highly semantically-aligned gesture labeling (50.2% accuracy) with efficient single-pass inference (0.4 seconds). The proposed method provides an interpretable intent reasoning pathway for semantic gesture synthesis.
format Preprint
id arxiv_https___arxiv_org_abs_2503_20202
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SARGes: Semantically Aligned Reliable Gesture Generation via Intent Chain
Gao, Nan
Bao, Yihua
Weng, Dongdong
Zhao, Jiayi
Li, Jia
Zhou, Yan
Wan, Pengfei
Zhang, Di
Computation and Language
Artificial Intelligence
Human-Computer Interaction
Robotics
Co-speech gesture generation enhances human-computer interaction realism through speech-synchronized gesture synthesis. However, generating semantically meaningful gestures remains a challenging problem. We propose SARGes, a novel framework that leverages large language models (LLMs) to parse speech content and generate reliable semantic gesture labels, which subsequently guide the synthesis of meaningful co-speech gestures.First, we constructed a comprehensive co-speech gesture ethogram and developed an LLM-based intent chain reasoning mechanism that systematically parses and decomposes gesture semantics into structured inference steps following ethogram criteria, effectively guiding LLMs to generate context-aware gesture labels. Subsequently, we constructed an intent chain-annotated text-to-gesture label dataset and trained a lightweight gesture label generation model, which then guides the generation of credible and semantically coherent co-speech gestures. Experimental results demonstrate that SARGes achieves highly semantically-aligned gesture labeling (50.2% accuracy) with efficient single-pass inference (0.4 seconds). The proposed method provides an interpretable intent reasoning pathway for semantic gesture synthesis.
title SARGes: Semantically Aligned Reliable Gesture Generation via Intent Chain
topic Computation and Language
Artificial Intelligence
Human-Computer Interaction
Robotics
url https://arxiv.org/abs/2503.20202