PulseAugur
中
实时 12:28:13
English(EN) DyaPlex: Full-Duplex Speech-Motion Model for Dyadic Interaction

DyaPlex模型同步语音和动作以实现双向交互

作者 PulseAugur 编辑部 · [2 个来源] ·

研究人员开发了DyaPlex，这是一种能够实时同步处理和生成语音及肢体动作的新型全双工模型。该模型集成了基础语音模型和新的动作通路，采用了双塔Transformer架构。DyaPlex在Seamless Interaction数据集上进行训练，实现了同步的多模态交互，并为双向人类交互设定了新基准。 AI

影响 引入了一种用于同步多模态AI交互的新架构，有望推动人机通信的发展。

排序理由 该集群包含一篇详细介绍新模型的学术论文。

在 arXiv cs.CV 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

报道来源 [2]

  1. arXiv cs.CV TIER_1 English(EN) · Koki Nagano, Hongyu Liu, Seonwook Park, Tianye Li, Amrita Mazumdar, Christian Jacobsen, Shengze Wang, Michael Stengel, Rajarshi Roy, Ka Chun Cheung, Simon See, Shalini De Mello ·

    DyaPlex: Full-Duplex Speech-Motion Model for Dyadic Interaction

    arXiv:2606.03874v1 Announce Type: new Abstract: We present DyaPlex, a streaming, full-duplex speech-and-motion model designed for dyadic interaction. To capture the continuous and reciprocal nature of human communication, this full-duplex capability empowers the agent to simultan…

  2. arXiv cs.CV TIER_1 English(EN) · Shalini De Mello ·

    DyaPlex: Full-Duplex Speech-Motion Model for Dyadic Interaction

    We present DyaPlex, a streaming, full-duplex speech-and-motion model designed for dyadic interaction. To capture the continuous and reciprocal nature of human communication, this full-duplex capability empowers the agent to simultaneously perceive and generate both speech and phy…

相关话题