LivelySpeaker: Towards Semantic-Aware Co-Speech Gesture Generation

doi:10.1109/ICCV51070.2023.01902

	LivelySpeaker: Towards Semantic-Aware Co-Speech Gesture Generation
	Yihao Zhi1 ; Xiaodong Cun 2; Xuelin Chen 2; Xi Shen 3; Wen Guo 4; Shaoli Huang 2; Shenghua Gao1
	2023-10-06
会议录名称	2023 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV)
ISSN	1550-5499
发表状态	已发表
DOI	10.1109/ICCV51070.2023.01902
摘要	Gestures are non-verbal but important behaviors accompanying people’s speech. While previous methods are able to generate speech rhythm-synchronized gestures, the semantic context of the speech is generally lacking in the gesticulations. Although semantic gestures do not occur very regularly in human speech, they are indeed the key for the audience to understand the speech context in a more immersive environment. Hence, we introduce LivelySpeaker, a framework that realizes semantics-aware co-speech gesture generation and offers several control handles. In particular, our method decouples the task into two stages: script-based gesture generation and audio-guided rhythm refinement. Specifically, the script-based gesture generation leverages the pre-trained CLIP text embeddings as the guidance for generating gestures that are highly semantically aligned with the script. Then, we devise a simple but effective diffusion-based gesture generation backbone simply using pure MLPs, that is conditioned on only audio signals and learns to gesticulate with realistic motions. We utilize such powerful prior to rhyme the script-guided gestures with the audio signals, notably in a zero-shot setting. Our novel two-stage generation framework also enables several applications, such as changing the gesticulation style, editing the co-speech gestures via textual prompting, and controlling the semantic awareness and rhythm alignment with guided diffusion. Extensive experiments demonstrate the advantages of the proposed framework over competing methods. In addition, our core diffusion-based generative model also achieves state-of-the-art performance on two benchmarks. The code and model will be released to facilitate future research.
关键词	Interpolation Computer vision Codes Semantics Benchmark testing Rhythm Generators
会议地点	Paris, France
会议日期	1-6 Oct. 2023
URL	查看原文
来源库	IEEE
引用统计	正在获取...
文献类型	会议论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/354918
专题	信息科学与技术学院_硕士生信息科学与技术学院_PI研究组_高盛华组
作者单位	1.ShanghaiTech University 2.Tencent AI Lab 3.Intellindust 4.INRIA
第一作者单位	上海科技大学
第一作者的第一单位	上海科技大学
推荐引用方式 GB/T 7714	Yihao Zhi,Xiaodong Cun,Xuelin Chen,et al. LivelySpeaker: Towards Semantic-Aware Co-Speech Gesture Generation[C],2023.