# The GENEA Challenge 2022: A large evaluation of data-driven co-speech gesture generation

arXiv: https://arxiv.org/abs/2208.10441 · HTML: https://mlsanity.com/paper/2208.10441/

## Key facts

- Cited by 40 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 68 references that are in the map.
- First posted on arXiv 22 Aug 2022.

## Builds on (most cited first, 20 of 20)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions](https://mlsanity.com/paper/1712.05884/) (2017)
- [Speech Gesture Generation from the Trimodal Context of Text, Audio, and Speaker Identity](https://mlsanity.com/paper/2009.02119/) (2020)
- [Robots Learn Social Skills: End-to-End Learning of Co-Speech Gesture Generation for Humanoid Robots](https://mlsanity.com/paper/1810.12541/) (2018)
- [Gesticulator: A framework for semantically-aware speech-driven gesture generation](https://mlsanity.com/paper/2001.09326/) (2020)
- [Speech2AffectiveGestures: Synthesizing Co-Speech Gestures with Generative Adversarial Affective Expression Learning](https://mlsanity.com/paper/2108.00262/) (2021)
- [Analyzing Input and Output Representations for Speech-Driven Gesture Generation](https://mlsanity.com/paper/1903.03369/) (2019)
- [A large, crowdsourced evaluation of gesture generation systems on common data: The GENEA Challenge 2020](https://mlsanity.com/paper/2102.11617/) (2021)
- [Let's Face It: Probabilistic Multi-modal Interlocutor-aware Generation of Facial Gestures in Dyadic Settings](https://mlsanity.com/paper/2006.09888/) (2020)
- [Deep Learning Based Assessment of Synthetic Speech Naturalness](https://mlsanity.com/paper/2104.11673/) (2021)
- [A Review of Evaluation Practices of Gesture Generation in Embodied Conversational Agents](https://mlsanity.com/paper/2101.03769/) (2021)
- [Integrated Speech and Gesture Synthesis](https://mlsanity.com/paper/2108.11436/) (2021)
- [Multimodal analysis of the predictability of hand-gesture properties](https://mlsanity.com/paper/2108.05762/) (2021)
- [HEMVIP: Human Evaluation of Multiple Videos in Parallel](https://mlsanity.com/paper/2101.11898/) (2021)
- [Speech2Properties2Gestures: Gesture-Property Prediction as a Tool for Generating Representational Gestures from Speech](https://mlsanity.com/paper/2106.14736/) (2021)
- [To Rate or Not To Rate: Investigating Evaluation Methods for Generated Co-Speech Gestures](https://mlsanity.com/paper/2108.05709/) (2021)
- [SGToolkit: An Interactive Gesture Authoring Toolkit for Embodied Conversational Agents](https://mlsanity.com/paper/2108.04636/) (2021)
- [Can we trust online crowdworkers? Comparing online and offline participants in a preference test of virtual agents](https://mlsanity.com/paper/2009.10760/) (2020)

## Built on by (most cited first, 30 of 40)

- [Listen, Denoise, Action! Audio-Driven Motion Synthesis with Diffusion Models](https://mlsanity.com/paper/2211.09707/) (2022)
- [GestureDiffuCLIP: Gesture Diffusion Model with CLIP Latents](https://mlsanity.com/paper/2303.14613/) (2023)
- [DiffuseStyleGesture: Stylized Audio-Driven Co-Speech Gesture Generation with Diffusion Models](https://mlsanity.com/paper/2305.04919/) (2023)
- [A Comprehensive Review of Data-Driven Co-Speech Gesture Generation](https://mlsanity.com/paper/2301.05339/) (2023)
- [QPGesture: Quantization-Based and Phase-Guided Motion Matching for Natural Speech-Driven Gesture Generation](https://mlsanity.com/paper/2305.11094/) (2023)
- [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)
- [Co-Speech Gesture Video Generation via Motion-Decoupled Diffusion Model](https://mlsanity.com/paper/2404.01862/) (2024)
- [GigaHands: A Massive Annotated Dataset of Bimanual Hand Activities](https://mlsanity.com/paper/2412.04244/) (2024)
- [Evaluating gesture generation in a large-scale open challenge: The GENEA Challenge 2022](https://mlsanity.com/paper/2303.08737/) (2023)
- [The GENEA Challenge 2023: A large scale evaluation of gesture generation models in monadic and dyadic settings](https://mlsanity.com/paper/2308.12646/) (2023)
- [Retrieving Semantics from the Deep: an RAG Solution for Gesture Synthesis](https://mlsanity.com/paper/2412.06786/) (2024)
- [DiffMotion: Speech-Driven Gesture Synthesis Using Denoising Diffusion Model](https://mlsanity.com/paper/2301.10047/) (2023)
- [What is the Best Automated Metric for Text to Motion Generation?](https://mlsanity.com/paper/2309.10248/) (2023)
- [Multiple Appropriate Facial Reaction Generation in Dyadic Interaction Settings: What, Why and How?](https://mlsanity.com/paper/2302.06514/) (2023)
- [REACT 2024: the Second Multiple Appropriate Facial Reaction Generation Challenge](https://mlsanity.com/paper/2401.05166/) (2024)
- [UnifiedGesture: A Unified Gesture Synthesis Model for Multiple Skeletons](https://mlsanity.com/paper/2309.07051/) (2023)
- [The DiffuseStyleGesture+ entry to the GENEA Challenge 2023](https://mlsanity.com/paper/2308.13879/) (2023)
- [Beyond Talking -- Generating Holistic 3D Human Dyadic Motion for Communication](https://mlsanity.com/paper/2403.19467/) (2024)
- [Diff-TTSG: Denoising probabilistic integrated speech and gesture synthesis](https://mlsanity.com/paper/2306.09417/) (2023)
- [The ReprGesture entry to the GENEA Challenge 2022](https://mlsanity.com/paper/2208.12133/) (2022)
- [AQ-GT: a Temporally Aligned and Quantized GRU-Transformer for Co-Speech Gesture Synthesis](https://mlsanity.com/paper/2305.01241/) (2023)
- [PersonaGesture: Single-Reference Co-Speech Gesture Personalization for Unseen Speakers](https://mlsanity.com/paper/2605.06064/) (2026)
- [GesGPT: Speech Gesture Synthesis With Text Parsing from ChatGPT](https://mlsanity.com/paper/2303.13013/) (2023)
- [Unified speech and gesture synthesis using flow matching](https://mlsanity.com/paper/2310.05181/) (2023)
- [HOP: Heterogeneous Topology-based Multimodal Entanglement for Co-Speech Gesture Generation](https://mlsanity.com/paper/2503.01175/) (2025)
- [Fake it to make it: Using synthetic data to remedy the data shortage in joint multimodal speech-and-gesture synthesis](https://mlsanity.com/paper/2404.19622/) (2024)
- [Stereo-Talker: Audio-driven 3D Human Synthesis with Prior-Guided Mixture-of-Experts](https://mlsanity.com/paper/2410.23836/) (2024)
- [MPE4G: Multimodal Pretrained Encoder for Co-Speech Gesture Generation](https://mlsanity.com/paper/2305.15740/) (2023)
- [A Survey on Deep Multi-modal Learning for Body Language Recognition and Generation](https://mlsanity.com/paper/2308.08849/) (2023)

## Abstract (arXiv)

This paper reports on the second GENEA Challenge to benchmark data-driven automatic co-speech gesture generation. Participating teams used the same speech and motion dataset to build gesture-generation systems. Motion generated by all these systems was rendered to video using a standardised visualisation pipeline and evaluated in several large, crowdsourced user studies. Unlike when comparing different research papers, differences in results are here only due to differences between methods, enabling direct comparison between systems. This year's dataset was based on 18 hours of full-body motion capture, including fingers, of different persons engaging in dyadic conversation. Ten teams participated in the challenge across two tiers: full-body and upper-body gesticulation. For each tier we evaluated both the human-likeness of the gesture motion and its appropriateness for the specific speech signal. Our evaluations decouple human-likeness from gesture appropriateness, which previously was a major challenge in the field. The evaluation results are a revolution, and a revelation. Some synthetic conditions are rated as significantly more human-like than human motion capture. To the best of our knowledge, this has never been shown before on a high-fidelity avatar. On the other hand, all synthetic motion is found to be vastly less appropriate for the speech than the original motion-capture recordings. Additional material is available via the project website at https://youngwoo-yoon.github.io/GENEAchallenge2022/