# DIDiffGes: Decoupled Semi-Implicit Diffusion Models for Real-time Gesture Generation from Speech

arXiv: https://arxiv.org/abs/2503.17059 · HTML: https://mlsanity.com/paper/2503.17059/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Audio, speech and music, one of 14 directions in Diffusion models.
- Builds on 24 of its 33 references that are in the map.
- First posted on arXiv 21 Mar 2025.

## Placed in

- Diffusion models / [Audio, speech and music](https://mlsanity.com/diffusion/audio-speech-and-music/)

## Builds on (most cited first, 24 of 24)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps](https://mlsanity.com/paper/2206.00927/) (2022)
- [MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model](https://mlsanity.com/paper/2208.15001/) (2022)
- [Executing your Commands via Motion Diffusion in Latent Space](https://mlsanity.com/paper/2212.04048/) (2022)
- [AI Choreographer: Music Conditioned 3D Dance Generation with AIST++](https://mlsanity.com/paper/2101.08779/) (2021)
- [Diffusion-GAN: Training GANs with Diffusion](https://mlsanity.com/paper/2206.02262/) (2022)
- [Speech Gesture Generation from the Trimodal Context of Text, Audio, and Speaker Identity](https://mlsanity.com/paper/2009.02119/) (2020)
- [Generating Holistic 3D Human Motion from Speech](https://mlsanity.com/paper/2212.04420/) (2022)
- [BEAT: A Large-Scale Semantic and Emotional Multi-Modal Dataset for Conversational Gestures Synthesis](https://mlsanity.com/paper/2203.05297/) (2022)
- [GestureDiffuCLIP: Gesture Diffusion Model with CLIP Latents](https://mlsanity.com/paper/2303.14613/) (2023)
- [Taming Diffusion Models for Audio-Driven Co-Speech Gesture Generation](https://mlsanity.com/paper/2303.09119/) (2023)
- [Learning Speech-driven 3D Conversational Gestures from Video](https://mlsanity.com/paper/2102.06837/) (2021)
- [DiffuseStyleGesture: Stylized Audio-Driven Co-Speech Gesture Generation with Diffusion Models](https://mlsanity.com/paper/2305.04919/) (2023)
- [ZeroEGGS: Zero-shot Example-based Gesture Generation from Speech](https://mlsanity.com/paper/2209.07556/) (2022)
- [Audio-Driven Co-Speech Gesture Video Generation](https://mlsanity.com/paper/2212.02350/) (2022)
- [The GENEA Challenge 2022: A large evaluation of data-driven co-speech gesture generation](https://mlsanity.com/paper/2208.10441/) (2022)
- [SignAvatars: A Large-scale 3D Sign Language Holistic Motion Dataset and Benchmark](https://mlsanity.com/paper/2310.20436/) (2023)
- [Freetalker: Controllable Speech and Text-Driven Gesture Generation Based on Diffusion Models for Enhanced Speaker Naturalness](https://mlsanity.com/paper/2401.03476/) (2024)
- [Semi-Implicit Denoising Diffusion Models (SIDDMs)](https://mlsanity.com/paper/2306.12511/) (2023)
- [Conditional GAN for Enhancing Diffusion Models in Efficient and Authentic Global Gesture Generation from Audios](https://mlsanity.com/paper/2410.20359/) (2024)
- [HoloGest: Decoupled Diffusion and Motion Priors for Generating Holisticly Expressive Co-speech Gestures](https://mlsanity.com/paper/2503.13229/) (2025)
- [ExpGest: Expressive Speaker Generation Using Diffusion Model and Hybrid Audio-Text Guidance](https://mlsanity.com/paper/2410.09396/) (2024)
- [RopeTP: Global Human Motion Recovery via Integrating Robust Pose Estimation with Diffusion Trajectory Prior](https://mlsanity.com/paper/2410.20358/) (2024)

## Built on by (most cited first, 3 of 3)

- [PhysDrift: Bridging the Embodiment Gap in Humanoid Co-Speech Motion Generation](https://mlsanity.com/paper/2606.19935/) (2026)
- [SmoothSync: Dual-Stream Diffusion Transformers for Jitter-Robust Beat-Synchronized Gesture Generation from Quantized Audio](https://mlsanity.com/paper/2601.04236/) (2026)
- [Inter-Diffusion Generation Model of Speakers and Listeners for Effective Communication](https://mlsanity.com/paper/2505.04996/) (2025)

## Abstract (arXiv)

Diffusion models have demonstrated remarkable synthesis quality and diversity in generating co-speech gestures. However, the computationally intensive sampling steps associated with diffusion models hinder their practicality in real-world applications. Hence, we present DIDiffGes, for a Decoupled Semi-Implicit Diffusion model-based framework, that can synthesize high-quality, expressive gestures from speech using only a few sampling steps. Our approach leverages Generative Adversarial Networks (GANs) to enable large-step sampling for diffusion model. We decouple gesture data into body and hands distributions and further decompose them into marginal and conditional distributions. GANs model the marginal distribution implicitly, while L2 reconstruction loss learns the conditional distributions exciplictly. This strategy enhances GAN training stability and ensures expressiveness of generated full-body gestures. Our framework also learns to denoise root noise conditioned on local body representation, guaranteeing stability and realism. DIDiffGes can generate gestures from speech with just 10 sampling steps, without compromising quality and expressiveness, reducing the number of sampling steps by a factor of 100 compared to existing methods. Our user study reveals that our method outperforms state-of-the-art approaches in human likeness, appropriateness, and style correctness. Project is https://cyk990422.github.io/DIDiffGes.