うなずき反応モデルを重畳したVirtualActorを介する身体的コミュニケーションの合成的解析(機械力学,計測,自動制御)

  • 瀬島 吉裕
    岡山県立大学大学院情報系工学研究科システム工学専攻
  • 渡辺 富夫
    岡山県立大学情報工学部情報システム工学科:科学技術振興機構戦略的創造研究推進事業
  • 山本 倫也
    関西学院大学理工学部人間システム工学科

書誌事項

タイトル別名
  • Analysis by Synthesis of Embodied Communication via VirtualActor with a Nodding Response Model(Mechanical Systems)
  • うなずき反応モデルを重畳したVirtualActorを介する身体的コミュニケーションの合成的解析
  • ウナズキ ハンノウ モデル オ チョウジョウ シタ VirtualActor オ カイスル シンタイテキ コミュニケーション ノ ゴウセイテキ カイセキ

この論文をさがす

抄録

We have already developed an embodied virtual communication system (EVCOS) for human interaction analysis by synthesis. This system provides two remote talkers with a communication environment in which embodied interaction is shared by VirtualActors (VAs) including the talkers themselves through a virtual face-to-face scene. We confirmed the importance of head movements including nodding in embodied communication by using this system. In this paper, we develop the EVCOS with a speech-driven nodding response model for the analysis by synthesis of embodied communication under the promoted condition of superimposed nodding responses in a virtual space. By using the system, we perform experiments for the effects of superimposed nodding responses by the sensory evaluation and the voice-motion analysis by superimposing nodding responses on VA by the nodding response model. It is found that the cross-correlation between the talker's voice and the listener's head motion in the inconsistently activated condition increases at a significance level of 1% compared to that observed under normal condition. The result demonstrates that the system with the model promotes embodied interaction.

収録刊行物

被引用文献 (1)*注記

もっと見る

参考文献 (25)*注記

もっと見る

関連プロジェクト

もっと見る

詳細情報 詳細情報について

問題の指摘

ページトップへ