Semantic Gesticulator: Semantics-Aware Co-Speech Gesture Synthesis

Abstract

In this work, we present Semantic Gesticulator, a novel framework designed to synthesize realistic gestures accompanying speech with strong semantic correspondence. Semantically meaningful gestures are crucial for effective non-verbal communication, but such gestures often fall within the long tail of the distribution of natural human motion. The sparsity of these movements makes it challenging for deep learning-based systems, trained on moderately sized datasets, to capture the relationship between the movements and the corresponding speech semantics. To address this challenge, we develop a generative retrieval framework based on a large language model. This framework efficiently retrieves suitable semantic gesture candidates from a motion library in response to the input speech. To construct this motion library, we summarize a comprehensive list of commonly used semantic gestures based on findings in linguistics, and we collect a high-quality motion dataset encompassing both body and hand movements. We also design a novel GPT-based model with strong generalization capabilities to audio, capable of generating high-quality gestures that match the rhythm of speech. Furthermore, we propose a semantic alignment mechanism to efficiently align the retrieved semantic gestures with the GPT's output, ensuring the naturalness of the final animation. Our system demonstrates robustness in generating gestures that are rhythmically coherent and semantically explicit, as evidenced by a comprehensive collection of examples. User studies confirm the quality and human-likeness of our results, and show that our system outperforms state-of-the-art systems in terms of semantic appropriateness by a clear margin.

SIGGRAPH 2024 (Journal Track); Project page: https://pku-mocca.github.io/Semantic-Gesticulator-Page

References in corpus (6)

• Speech Gesture Generation from the Trimodal Context of Text, Audio, and Speaker Identity
• The GENEA Challenge 2022: A large evaluation of data-driven co-speech gesture generation
• CorpusBrain: Pre-train a Generative Retrieval Model for Knowledge-Intensive Language Tasks
• Speech2Properties2Gestures: Gesture-Property Prediction as a Tool for Generating Representational Gestures from Speech
• Diffusion-Based Co-Speech Gesture Generation Using Joint Text and Audio Representation
• BodyFormer: Semantics-guided 3D Body Gesture Synthesis with Transformer

Cited by in corpus (4)

• Synchronize Dual Hands for Physics-Based Dexterous Guitar Playing
• Semantics-Aware Human Motion Generation from Audio Instructions
• GestureCoach: Rehearsing for Engaging Talks with LLM-Driven Gesture Recommendations
• InterAct: A Large-Scale Dataset of Dynamic, Expressive and Interactive Activities between Two People in Daily Scenarios