论文学习
Style-Controllable Speech-Driven Gesture Synthesis Using

发布于44个月以前

  • 0
  • 0
  • 176

发布于44个月以前

Style-Controllable Speech-Driven Gesture Synthesis Using Normalising Flows

Automatic synthesis of realistic gestures promises to transform the fields of animation, avatars and communicative agents. In off-line applications, novel tools can alter the role of an animator to that of a director, who provides only high-level input for the desired animation; a learned network then translates these instructions into an appropriate sequence of body poses. In interactive scenarios, systems for generating natural animations on the fly are key to achieving believable and relatable characters. In this paper we address some of the core issues towards these ends. By adapting a deep learning-based motion synthesis method called MoGlow, we propose a new generative model for generating state-of-the-art realistic speech-driven gesticulation. Owing to the probabilistic nature of the approach, our model can produce a battery of different, yet plausible, gestures given the same input speech signal. Just like humans, this gives a rich natural variation of motion. We additionally demonstrate the ability to exert directorial control over the output style, such as gesture level, speed, symmetry and spacial extent. Such control can be leveraged to convey a desired character personality or mood. We achieve all this without any manual annotation of the data. User studies evaluating upper-body gesticulation confirm that the generated motions are natural and well match the input speech. Our method scores above all prior systems and baselines on these measures, and comes close to the ratings of the original recorded motions. We furthermore find that we can accurately control gesticulation styles without unnecessarily compromising perceived naturalness. Finally, we also demonstrate an application of the same method to full-body gesticulation, including the synthesis of stepping motion and stance.

论文下载

论文地址:https://diglib.eg.org/handle/10.1111/cgf13946

算法链接

算法https://marketplace.huaweicloud.com/markets/aihub/modelhub/detail/?id=9256a610-0912-4106-9ed4-087a99fc58dd

算法指南

算法指南https://bbs.huaweicloud.com/forum/thread-93372-1-1.html

评论 0

登录后评论

    euuufe

    作者相关内容

    2021第三届华为云人工智能大赛无人车挑战杯学习资料
    发布于44个月以前
    华为云AI论文精读会2021第二十期:轻量化神经网络MobileNet系列论文精读
    发布于41个月以前
    [华为云AI经典论文复现] AI Gallery CrowdDet算法使用介绍
    发布于42个月以前
    华为云AI论文精读会2021第四期:Dynamic RCNN:一种有效提升RCNN系列网络表现的动态训练方法
    发布于42个月以前
    华为云AI论文精读会2021第十九期:ACGAN-动漫头像生成
    发布于41个月以前

    暂无数据

    热门内容推荐

    快速体验10个精选论文复现算法模型,赢取蓝牙音箱、体脂秤、ModelArts图书!
    WAYNE 发布于44个月以前
    华为云AI论文精读会2021第二十期:轻量化神经网络MobileNet系列论文精读
    euuufe 发布于41个月以前
    [华为云AI经典论文复现] AI Gallery CrowdDet算法使用介绍
    euuufe 发布于42个月以前
    Fast-SCNN: Fast Semantic Segmentation Network
    spy 发布于44个月以前
    华为云AI论文精读会2021第四期:Dynamic RCNN:一种有效提升RCNN系列网络表现的动态训练方法
    euuufe 发布于42个月以前

    暂无数据