# BodyFormer: Semantics-guided 3D Body Gesture Synthesis with Transformer

arXiv: https://arxiv.org/abs/2310.06851 · HTML: https://mlsanity.com/paper/2310.06851/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 57 references that are in the map.
- First posted on arXiv 7 Sep 2023.

## Builds on (most cited first, 30 of 31)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context](https://mlsanity.com/paper/1901.02860/) (2019)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [On the Continuity of Rotation Representations in Neural Networks](https://mlsanity.com/paper/1812.07035/) (2018)
- [Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books](https://mlsanity.com/paper/1506.06724/) (2015)
- [Transformers in Vision: A Survey](https://mlsanity.com/paper/2101.01169/) (2021)
- [Speech Gesture Generation from the Trimodal Context of Text, Audio, and Speaker Identity](https://mlsanity.com/paper/2009.02119/) (2020)
- [Cyclical Annealing Schedule: A Simple Approach to Mitigating KL Vanishing](https://mlsanity.com/paper/1903.10145/) (2019)
- [Learning Individual Styles of Conversational Gesture](https://mlsanity.com/paper/1906.04160/) (2019)
- [BEAT: A Large-Scale Semantic and Emotional Multi-Modal Dataset for Conversational Gestures Synthesis](https://mlsanity.com/paper/2203.05297/) (2022)
- [Taming Diffusion Models for Audio-Driven Co-Speech Gesture Generation](https://mlsanity.com/paper/2303.09119/) (2023)
- [Robots Learn Social Skills: End-to-End Learning of Co-Speech Gesture Generation for Humanoid Robots](https://mlsanity.com/paper/1810.12541/) (2018)
- [Audio2Gestures: Generating Diverse Gestures from Speech Audio with Conditional Variational Autoencoders](https://mlsanity.com/paper/2108.06720/) (2021)
- [Learning Hierarchical Cross-Modal Association for Co-Speech Gesture Generation](https://mlsanity.com/paper/2203.13161/) (2022)
- [Text2Gestures: A Transformer-Based Network for Generating Emotive Body Gestures for Virtual Agents](https://mlsanity.com/paper/2101.11101/) (2021)
- [Learning Speech-driven 3D Conversational Gestures from Video](https://mlsanity.com/paper/2102.06837/) (2021)
- [Gesticulator: A framework for semantically-aware speech-driven gesture generation](https://mlsanity.com/paper/2001.09326/) (2020)
- [ZeroEGGS: Zero-shot Example-based Gesture Generation from Speech](https://mlsanity.com/paper/2209.07556/) (2022)
- [Style Transfer for Co-Speech Gesture Animation: A Multi-Speaker Conditional-Mixture Approach](https://mlsanity.com/paper/2007.12553/) (2020)
- [Speech2AffectiveGestures: Synthesizing Co-Speech Gestures with Generative Adversarial Affective Expression Learning](https://mlsanity.com/paper/2108.00262/) (2021)
- [Speech Drives Templates: Co-Speech Gesture Synthesis with Learned Templates](https://mlsanity.com/paper/2108.08020/) (2021)
- [Analyzing Input and Output Representations for Speech-Driven Gesture Generation](https://mlsanity.com/paper/1903.03369/) (2019)
- [Audio to Body Dynamics](https://mlsanity.com/paper/1712.09382/) (2017)
- [MoGlow: Probabilistic and controllable motion synthesis using normalising flows](https://mlsanity.com/paper/1905.06598/) (2019)
- [A large, crowdsourced evaluation of gesture generation systems on common data: The GENEA Challenge 2020](https://mlsanity.com/paper/2102.11617/) (2021)
- [Rhythmic Gesticulator: Rhythm-Aware Co-Speech Gesture Synthesis with Hierarchical Neural Embeddings](https://mlsanity.com/paper/2210.01448/) (2022)
- [Transflower: probabilistic autoregressive dance generation with multimodal attention](https://mlsanity.com/paper/2106.13871/) (2021)

## Built on by (most cited first, 21 of 21)

- [EMAGE: Towards Unified Holistic Co-Speech Gesture Generation via Expressive Masked Audio Gesture Modeling](https://mlsanity.com/paper/2401.00374/) (2023)
- [EMDM: Efficient Motion Diffusion Model for Fast and High-Quality Motion Generation](https://mlsanity.com/paper/2312.02256/) (2023)
- [MambaTalk: Efficient Holistic Gesture Synthesis with Selective State Space Models](https://mlsanity.com/paper/2403.09471/) (2024)
- [Semantic Gesticulator: Semantics-Aware Co-Speech Gesture Synthesis](https://mlsanity.com/paper/2405.09814/) (2024)
- [Emotional Speech-driven 3D Body Animation via Disentangled Latent Diffusion](https://mlsanity.com/paper/2312.04466/) (2023)
- [TANGO: Co-Speech Gesture Video Reenactment with Hierarchical Audio Motion Embedding and Diffusion Interpolation](https://mlsanity.com/paper/2410.04221/) (2024)
- [DiffTED: One-shot Audio-driven TED Talk Video Generation with Diffusion-based Co-speech Gestures](https://mlsanity.com/paper/2409.07649/) (2024)
- [SemGes: Semantics-aware Co-Speech Gesture Generation using Semantic Coherence and Relevance Learning](https://mlsanity.com/paper/2507.19359/) (2025)
- [A Unified Framework for Multimodal, Multi-Part Human Motion Synthesis](https://mlsanity.com/paper/2311.16471/) (2023)
- [Social Agent: Mastering Dyadic Nonverbal Behavior Generation via Conversational LLM Agents](https://mlsanity.com/paper/2510.04637/) (2025)
- [DyaDiT: A Multi-Modal Diffusion Transformer for Socially Favorable Dyadic Gesture Generation](https://mlsanity.com/paper/2602.23165/) (2026)
- [InterAct: Capture and Modelling of Realistic, Expressive and Interactive Activities between Two Persons in Daily Scenarios](https://mlsanity.com/paper/2405.11690/) (2024)
- [Efficient Text-driven Motion Generation via Latent Consistency Training](https://mlsanity.com/paper/2405.02791/) (2024)
- [Stereo-Talker: Audio-driven 3D Human Synthesis with Prior-Guided Mixture-of-Experts](https://mlsanity.com/paper/2410.23836/) (2024)
- [CoordSpeaker: Exploiting Gesture Captioning for Coordinated Caption-Empowered Co-Speech Gesture Generation](https://mlsanity.com/paper/2511.22863/) (2025)
- [Towards a GENEA Leaderboard -- an Extended, Living Benchmark for Evaluating and Advancing Conversational Motion Synthesis](https://mlsanity.com/paper/2410.06327/) (2024)
- [Cosh-DiT: Co-Speech Gesture Video Synthesis via Hybrid Audio-Visual Diffusion Transformers](https://mlsanity.com/paper/2503.09942/) (2025)
- [InterAct: A Large-Scale Dataset of Dynamic, Expressive and Interactive Activities between Two People in Daily Scenarios](https://mlsanity.com/paper/2509.05747/) (2025)
- [U-Mind: A Unified Framework for Real-Time Multimodal Interaction with Audiovisual Generation](https://mlsanity.com/paper/2602.23739/) (2026)
- [Towards Reliable Human Evaluations in Gesture Generation: Insights from a Community-Driven State-of-the-Art Benchmark](https://mlsanity.com/paper/2511.01233/) (2025)
- [Joint Co-Speech Gesture and Expressive Talking Face Generation using Diffusion with Adapters](https://mlsanity.com/paper/2412.14333/) (2024)

## Abstract (arXiv)

Automatic gesture synthesis from speech is a topic that has attracted researchers for applications in remote communication, video games and Metaverse. Learning the mapping between speech and 3D full-body gestures is difficult due to the stochastic nature of the problem and the lack of a rich cross-modal dataset that is needed for training. In this paper, we propose a novel transformer-based framework for automatic 3D body gesture synthesis from speech. To learn the stochastic nature of the body gesture during speech, we propose a variational transformer to effectively model a probabilistic distribution over gestures, which can produce diverse gestures during inference. Furthermore, we introduce a mode positional embedding layer to capture the different motion speeds in different speaking modes. To cope with the scarcity of data, we design an intra-modal pre-training scheme that can learn the complex mapping between the speech and the 3D gesture from a limited amount of data. Our system is trained with either the Trinity speech-gesture dataset or the Talking With Hands 16.2M dataset. The results show that our system can produce more realistic, appropriate, and diverse body gestures compared to existing state-of-the-art approaches.