# StreamTalk: Streaming Co-Speech Gesture Generation with Key-Pose Anchoring

arXiv: https://arxiv.org/abs/2608.01643 · HTML: https://mlsanity.com/paper/2608.01643/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 63 of its 72 references that are in the map.
- First posted on arXiv 3 Aug 2026.

## Builds on (most cited first, 30 of 63)

- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [Expressive Body Capture: 3D Hands, Face, and Body from a Single Image](https://mlsanity.com/paper/1904.05866/) (2019)
- [On the Continuity of Rotation Representations in Neural Networks](https://mlsanity.com/paper/1812.07035/) (2018)
- [Autoregressive Image Generation using Residual Quantization](https://mlsanity.com/paper/2203.01941/) (2022)
- [AI Choreographer: Music Conditioned 3D Dance Generation with AIST++](https://mlsanity.com/paper/2101.08779/) (2021)
- [Human Motion Diffusion as a Generative Prior](https://mlsanity.com/paper/2303.01418/) (2023)
- [ReMoDiffuse: Retrieval-Augmented Motion Diffusion Model](https://mlsanity.com/paper/2304.01116/) (2023)
- [Speech Gesture Generation from the Trimodal Context of Text, Audio, and Speaker Identity](https://mlsanity.com/paper/2009.02119/) (2020)
- [Listen, Denoise, Action! Audio-Driven Motion Synthesis with Diffusion Models](https://mlsanity.com/paper/2211.09707/) (2022)
- [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)
- [TEACH: Temporal Action Composition for 3D Humans](https://mlsanity.com/paper/2209.04066/) (2022)
- [GestureDiffuCLIP: Gesture Diffusion Model with CLIP Latents](https://mlsanity.com/paper/2303.14613/) (2023)
- [Audio2Gestures: Generating Diverse Gestures from Speech Audio with Conditional Variational Autoencoders](https://mlsanity.com/paper/2108.06720/) (2021)
- [EMAGE: Towards Unified Holistic Co-Speech Gesture Generation via Expressive Masked Audio Gesture Modeling](https://mlsanity.com/paper/2401.00374/) (2023)
- [Learning Speech-driven 3D Conversational Gestures from Video](https://mlsanity.com/paper/2102.06837/) (2021)
- [MotionStreamer: Streaming Motion Generation via Diffusion-based Autoregressive Model in Causal Latent Space](https://mlsanity.com/paper/2503.15451/) (2025)
- [DiffuseStyleGesture: Stylized Audio-Driven Co-Speech Gesture Generation with Diffusion Models](https://mlsanity.com/paper/2305.04919/) (2023)
- [From Audio to Photoreal Embodiment: Synthesizing Humans in Conversations](https://mlsanity.com/paper/2401.01885/) (2024)
- [DiffSHEG: A Diffusion-Based Approach for Real-Time Speech-driven Holistic 3D Expression and Gesture Generation](https://mlsanity.com/paper/2401.04747/) (2024)
- [Lodge: A Coarse to Fine Diffusion Network for Long Dance Generation Guided by the Characteristic Dance Primitives](https://mlsanity.com/paper/2403.10518/) (2024)
- [MambaTalk: Efficient Holistic Gesture Synthesis with Selective State Space Models](https://mlsanity.com/paper/2403.09471/) (2024)
- [GestureLSM: Latent Shortcut based Co-Speech Gesture Generation with Spatial-Temporal Modeling](https://mlsanity.com/paper/2501.18898/) (2025)
- [LivelySpeaker: Towards Semantic-Aware Co-Speech Gesture Generation](https://mlsanity.com/paper/2309.09294/) (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)
- [Skinned Motion Retargeting with Residual Perception of Motion Semantics & Geometry](https://mlsanity.com/paper/2303.08658/) (2023)

## Abstract (arXiv)

Real-time co-speech gesture generation must produce 3D motion clip by clip as speech arrives. Existing streaming methods are open-loop: each clip depends on past context, but the model cannot check or correct its trajectory. Small errors therefore accumulate and cause drift over long sequences. We observe that this failure is mainly caused by the lack of a forward constraint rather than poor short-clip quality. A plausible key pose at the end of each clip provides a destination anchor that limits drift. Based on this observation, we propose StreamTalk, a closed-loop framework with a periodic generate-retrieve-refine cycle. Streaming Pose-Guided Generation first predicts a coarse clip, retrieves a plausible tail pose from a speaker-specific motion database, and refines the clip using this pose before continuing to the next window. During training, Stochastic Anchor Masking randomly masks pose and translation frames, teaching the model to recover complete motion from sparse boundary conditions. A part-aware DiT separates hand, body, and translation streams to reduce interference between global displacement and local articulation. On BEAT2, StreamTalk achieves state-of-the-art FGD, reduces long-horizon drift relative to open-loop baselines, and runs in real time at 76 FPS. Project page: https://xiangyue-zhang.github.io/StreamTalk/.