GesGPT: Speech Gesture Synthesis With Text Parsing From ChatGPT

doi:10.1109/LRA.2024.3359544

CASIA OpenIR > 数字内容技术与服务研究中心 > 版权智能与文化计算

	GesGPT: Speech Gesture Synthesis With Text Parsing From ChatGPT
	Gao, Nan1 ; Zhao, Zeyu 1,2; Zeng, Zhi3 ; Zhang, Shuwu3 ; Weng, Dongdong 4,5; Bao, Yihua 4,5
发表期刊	IEEE ROBOTICS AND AUTOMATION LETTERS
ISSN	2377-3766
	2024-03-01
卷号	9 期号:3 页码:2718-2725
通讯作者	Bao, Yihua(boye1900@outlook.com)
摘要	Gesture synthesis has gained significant attention as a critical research field, aiming to produce contextually appropriate and natural gestures corresponding to speech or textual input. Although deep learning-based approaches have achieved remarkable progress, they often overlook the rich semantic information present in the text, leading to less expressive and meaningful gestures. In this letter, we propose GesGPT, a novel approach to gesture generation that leverages the semantic analysis capabilities of large language models, such as ChatGPT. By capitalizing on the strengths of LLMs for text analysis, we adopt a controlled approach to generate and integrate professional gestures and base gestures through a text parsing script, resulting in diverse and meaningful gestures. Firstly, our approach involves the development of prompt principles that transform gesture generation into an intention classification problem using ChatGPT. We also conduct further analysis on emphasis words and semantic words to aid in gesture generation. Subsequently, we construct a specialized gesture lexicon with multiple semantic annotations, decoupling the synthesis of gestures into professional gestures and base gestures. Finally, we merge the professional gestures with base gestures. Experimental results demonstrate that GesGPT effectively generates contextually appropriate and expressive gestures.
关键词	Semantics Chatbots Task analysis Robots Deep learning Cognition Annotations Gesture synthesis human robot interaction large language model
DOI	10.1109/LRA.2024.3359544
收录类别	SCI
语种	英语
资助项目	National Key Ramp;D Program of China
项目资助者	National Key Ramp;D Program of China
WOS研究方向	Robotics
WOS类目	Robotics
WOS记录号	WOS:001174114300007
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/56988
专题	数字内容技术与服务研究中心_版权智能与文化计算
通讯作者	Bao, Yihua
作者单位	1.Chinese Acad Sci, Inst Automat, Beijing 100045, Peoples R China 2.Univ Chinese Acad Sci, Beijing 101408, Peoples R China 3.Beijing Univ Posts & Telecommun, Beijing 100876, Peoples R China 4.Beijing Engn Res Ctr Mixed Real & Adv Display, Beijing 100081, Peoples R China 5.Inst Technol Beijing, Beijing 100081, Peoples R China
第一作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Gao, Nan,Zhao, Zeyu,Zeng, Zhi,et al. GesGPT: Speech Gesture Synthesis With Text Parsing From ChatGPT[J]. IEEE ROBOTICS AND AUTOMATION LETTERS,2024,9(3):2718-2725.
APA	Gao, Nan,Zhao, Zeyu,Zeng, Zhi,Zhang, Shuwu,Weng, Dongdong,&Bao, Yihua.(2024).GesGPT: Speech Gesture Synthesis With Text Parsing From ChatGPT.IEEE ROBOTICS AND AUTOMATION LETTERS,9(3),2718-2725.
MLA	Gao, Nan,et al."GesGPT: Speech Gesture Synthesis With Text Parsing From ChatGPT".IEEE ROBOTICS AND AUTOMATION LETTERS 9.3(2024):2718-2725.