[
    {
        "id": "osp-24727",
        "type": "article-journal",
        "title": "SocialHumanoid: Towards Expressive Humanoid Behavior via One-Step Co-Speech Motion Generation",
        "author": [
            {
                "family": "Yang",
                "given": "Chengqun"
            },
            {
                "family": "Zhu",
                "given": "Tengjie"
            },
            {
                "family": "Xu",
                "given": "Liang"
            },
            {
                "family": "Liu",
                "given": "Fulong"
            },
            {
                "family": "Ren",
                "given": "Guanzhu"
            },
            {
                "family": "Xing",
                "given": "Yitong"
            },
            {
                "family": "Lu",
                "given": "Xuefeng"
            },
            {
                "family": "Shi",
                "given": "Fei"
            },
            {
                "family": "Fan",
                "given": "Siyuan"
            },
            {
                "family": "Dong",
                "given": "Weijie"
            },
            {
                "family": "Mu",
                "given": "Yao"
            },
            {
                "family": "Yang",
                "given": "Xiaokang"
            },
            {
                "family": "Yan",
                "given": "Yichao"
            }
        ],
        "URL": "https://omanscience.com/en/articles/socialhumanoid-towards-expressive-humanoid-behavior-via-one-step-co-speech-motion-generation",
        "language": "en",
        "issued": {
            "date-parts": [
                [
                    2026
                ]
            ]
        },
        "abstract": "Humanoid robots are increasingly expected to serve as embodied social agents that communicate naturally with humans through face-to-face interaction. During such communication, humanoid robots require body behaviors that are synchronized with speech, affectively expressive, and suitable for real-time execution. However, existing co-speech methods are primarily developed for digital humans and lack joint support for affective control and low-latency continuous generation on physical embodiments. To bridge this gap, we present SocialHumanoid, a system for expressive humanoid behavior via one-step co-speech motion generation. Given response speech and a specified affective condition, SocialHumanoid generates each full-body motion window in a single forward pass and connects successive windows through motion-history conditioning. The generated human motion is further converted online into embodiment-compatible robot references and tracked by a whole-body controller for physical execution. To provide explicit supervision for affective body expression, we further introduce AffectMoCap, a 4-hour dataset captured from two professional actors, containing synchronized speech, body motion, fine-grained hand motion, and emotion annotations. On BEAT2, SocialHumanoid achieves the best FGD among the compared generation methods, competitive speech-motion synchrony, and approximately $6\\times$ faster inference than GestureLSM under the same protocol. Perceptual evaluations further show that training with AffectMoCap improves affect recognition from generated body motion, while real-robot experiments demonstrate continuous affect-conditioned behavior and stable long-horizon execution. Our project page is https://rex0191.github.io/SocialHumanoid/."
    }
]