论文/arXiv 2609.39575·28 天前

ECHO-G：具身共语音人形机器人动作生成

ECHO-G用音频与定时转录联合条件的扩散Transformer生成全身共语音人形机器人动作，并在数据集、基准和实体机器人上验证。

AI 整理

• 数据与采集
• 具身模型
• 端侧部署

原文链接：ECHO-G: Embodied Co-speech Humanoid mOtion Generation（arXiv 2609.39575 · 发布日期：2026-09-30）

ECHO-G: Embodied Co-speech Humanoid mOtion Generation

ECHO-G用音频与定时转录联合条件的扩散Transformer生成全身共语音人形机器人动作，并在数据集、基准和实体机器人上验证。

核心要点

• 全身共语音人形机器人动作生成需同时协调韵律、语言内容和具身动作。
• SGDiT以音频和定时转录为条件，融合帧级声学与词级语言上下文。
• 引入BEAT2衍生数据集与基准；评测支持直接机器人空间生成和音文联合条件。
• 已在物理人形机器人部署，并开放数据集及训练、推理、评估代码。

验证范围与局限：验证范围为BEAT2衍生数据集基准、视频评分研究和物理人形机器人部署。

英文摘要 (Abstract)

Generating full-body co-speech motion for humanoid robots requires coordinating speech prosody, linguistic content, and embodiment-specific motion. To this end, we present ECHO-G, a framework jointly conditioned on speech audio and timed transcripts. Its Speech-Grounded Diffusion Transformer (SGDiT) combines frame-aligned acoustic features with token-level linguistic context, preserving their distinct granularities. Trained with rectified flow matching, it models one-to-many utterance-motion relationships directly in robot space. To support training and evaluation, we introduce a BEAT2-derived audio-text-robot dataset and a benchmark covering co-speech characteristics, robot-motion quality, and runtime efficiency. Comparative evaluation supports direct robot-space generation over the evaluated human-motion generation and retargeting pipelines, while modality ablations highlight the benefits of joint audio-text conditioning. We further demonstrate deployment on a physical humanoid robot. A complementary video-rating study also favors joint conditioning over the alternatives. The dataset and training, inference, and evaluation code are available through our project page.

作者：Yizhao Li, Pusen Gao, Ming Wang, Shaojie Shen, Shuo Yang, Hao Xu

来源

本页事实对应的公开页面，以原文为准。

1. arXiv 2609.39575：ECHO-G: Embodied Co-speech Humanoid mOtion Generation访问 2026-10-21