# RoboGesture: Real-Time Semantic-aligned Co-Speech Gestures Generation for Humanoid Interaction

arXiv: https://arxiv.org/abs/2608.28693 · HTML: https://mlsanity.com/paper/2608.28693/

## 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 32 of its 50 references that are in the map.
- First posted on arXiv 27 Aug 2026.

## Placed in

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

## Builds on (most cited first, 30 of 32)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [Moshi: a speech-text foundation model for real-time dialogue](https://mlsanity.com/paper/2410.00037/) (2024)
- [AI Choreographer: Music Conditioned 3D Dance Generation with AIST++](https://mlsanity.com/paper/2101.08779/) (2021)
- [Seed-TTS: A Family of High-Quality Versatile Speech Generation Models](https://mlsanity.com/paper/2406.02430/) (2024)
- [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)
- [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)
- [AnyTeleop: A General Vision-Based Dexterous Robot Arm-Hand Teleoperation System](https://mlsanity.com/paper/2307.04577/) (2023)
- [Robots Learn Social Skills: End-to-End Learning of Co-Speech Gesture Generation for Humanoid Robots](https://mlsanity.com/paper/1810.12541/) (2018)
- [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)
- [Retargeting Matters: General Motion Retargeting for Humanoid Motion Tracking](https://mlsanity.com/paper/2510.02252/) (2025)
- [OmniRetarget: Interaction-Preserving Data Generation for Humanoid Whole-Body Loco-Manipulation and Scene Interaction](https://mlsanity.com/paper/2509.26633/) (2025)
- [DiffSHEG: A Diffusion-Based Approach for Real-Time Speech-driven Holistic 3D Expression and Gesture Generation](https://mlsanity.com/paper/2401.04747/) (2024)
- [Digital Life Project: Autonomous 3D Characters with Social Intelligence](https://mlsanity.com/paper/2312.04547/) (2023)
- [Semantic Gesticulator: Semantics-Aware Co-Speech Gesture Synthesis](https://mlsanity.com/paper/2405.09814/) (2024)
- [SemTalk: Holistic Co-speech Motion Generation with Frame-level Semantic Emphasis](https://mlsanity.com/paper/2412.16563/) (2024)
- [SOLAMI: Social Vision-Language-Action Modeling for Immersive Interaction with 3D Autonomous Characters](https://mlsanity.com/paper/2412.00174/) (2024)
- [EchoMask: Speech-Queried Attention-based Mask Modeling for Holistic Co-Speech Motion Generation](https://mlsanity.com/paper/2504.09209/) (2025)
- [SemGes: Semantics-aware Co-Speech Gesture Generation using Semantic Coherence and Relevance Learning](https://mlsanity.com/paper/2507.19359/) (2025)
- [iCub3 Avatar System: Enabling Remote Fully-Immersive Embodiment of Humanoid Robots](https://mlsanity.com/paper/2203.06972/) (2022)
- [GenH2R: Learning Generalizable Human-to-Robot Handover via Scalable Simulation, Demonstration, and Imitation](https://mlsanity.com/paper/2401.00929/) (2024)
- [Mitigating Error Accumulation in Co-Speech Motion Generation via Global Rotation Diffusion and Multi-Level Constraints](https://mlsanity.com/paper/2511.10076/) (2025)
- [Robot Interaction Behavior Generation based on Social Motion Forecasting for Human-Robot Interaction](https://mlsanity.com/paper/2402.04768/) (2024)

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

- [SocialHumanoid: Towards Expressive Humanoid Behavior via One-Step Co-Speech Motion Generation](https://mlsanity.com/paper/2609.33311/) (2026)
- [GestAdapt: Workspace-Conditioned Co-Speech Gesture Generation for Humanoid Robots](https://mlsanity.com/paper/2609.38400/) (2026)
- [ECHO-G: Embodied Co-speech Humanoid mOtion Generation](https://mlsanity.com/paper/2609.39575/) (2026)

## Abstract (arXiv)

Enabling humanoid robots to respond to human speech with synchronized and semantically meaningful gestures is fundamental to natural human-robot interaction. However, this task faces three critical barriers: the scarcity of semantically rich datasets, the "modality eclipse" where models ignore audio cues in favor of kinematic inertia, and the sim-to-real gap regarding physical safety. We propose RoboGesture, a robot-centric framework that co-designs data, modeling, and control to power a complete interactive human-humanoid system in which the robot listens, responds, and gestures in real time. We first establish the RoboGesture dataset featuring over 300 gesture categories and develop an automated pipeline to synthesize large-scale collision-free, robot-specific audio-motion pairs. Our architecture features a Hierarchical Semantic-Acoustic Aligner that extracts multi-granular prosodic and semantic cues directly from raw audio tokens. These cues drive a Streaming Conditional Motion Generator based on a diffusion transformer with conditional flow matching. To ensure high responsiveness, we introduce Anti-Inertia CFG Masking, which prevents the model from collapsing into repetitive historical patterns by compelling it to proactively mine control signals from the audio modality. Finally, an MPC-based safety filter ensures real-time, collision-free execution on physical hardware. Experiments on a Unitree G1 humanoid demonstrate that RoboGesture generates safer, more rhythmic, and more semantically appropriate responses compared to state-of-the-art baselines.