你会即兴吗？通过音频控制的富有表现力的人形机器人运动
Do You Have Freestyle? Expressive Humanoid Locomotion via Audio Control
把音频当作隐式风格信号、跳过显式动作重建直接生成可执行的人形运动，这种「内容+风格」解耦的音频到运动扩散策略可迁移到视觉侧的音频驱动人体动作生成与动作重定向任务，避免级联误差与高延迟。
原文依据 We propose RoboPerform, the first unified audio-to-locomotion framework that can directly generate music-driven dance and speech-driven co-speech gestures from audio.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论人类会本能地随声音律动，但当前的人形机器人缺乏富有表现力的即兴能力，只能局限于预定义动作或稀疏指令。先从音频生成动作、再将其重定向到机器人的做法依赖显式的动作重建，会导致级联误差、高延迟以及声学与驱动之间割裂的映射关系。我们提出 RoboPerform，这是首个统一的音频到运动框架，可直接从音频生成音乐驱动的舞蹈与语音驱动的伴随手势。该框架以「运动 = 内容 + 风格」为核心原则，将音频视为隐式风格信号，从而无需显式动作重建。RoboPerform 集成了一个用于适应多样运动模式的 ResMoE 教师策略，以及一个用于注入音频风格的基于扩散的学生策略。这种免重定向的设计保证了低延迟与高保真。实验验证表明，RoboPerform 在物理合理性与音频对齐方面取得了良好结果，成功将机器人转变为能够对音频做出反应的即兴表演者。
英文原文摘要 1127 字符
Humans intuitively move to sound, but current humanoid robots lack expressive improvisational capabilities, confined to predefined motions or sparse commands. Generating motion from audio and then retargeting it to robots relies on explicit motion reconstruction, leading to cascaded errors, high latency, and disjointed acoustic-actuation mapping. We propose RoboPerform, the first unified audio-to-locomotion framework that can directly generate music-driven dance and speech-driven co-speech gestures from audio. Guided by the core principle of "motion = content + style", the framework treats audio as implicit style signals and eliminates the need for explicit motion reconstruction. RoboPerform integrates a ResMoE teacher policy for adapting to diverse motion patterns and a diffusion-based student policy for audio style injection. This retargeting-free design ensures low latency and high fidelity. Experimental validation shows that RoboPerform achieves promising results in physical plausibility and audio alignment, successfully transforming robots into responsive freestyle performers capable of reacting to audio.