条件付き確率場を用いた発話テキストに対するジェスチャの推定

カテゴリ: 論文誌(論文単位)

グループ名: 【C】電子・情報・システム部門

発行日: 2016/03/01

タイトル(英語): Estimation of Gestures for Utterance Text Using Conditional Random Fields

著者名: 塙　俊樹（青山学院大学 理工学研究科），白川　真一（筑波大学 システム情報系），長谷川　大（青山学院大学 理工学部），塩入　直哉（青山学院大学 理工学研究科），大原　剛三（青山学院大学 理工学部），佐久田　博司（青山学院大学 理工学部）

著者名(英語): Toshiki Hanawa (Graduate School of Science and Engineering, Aoyama Gakuin University), Shinichi Shirakawa (Faculty of Engineering, Information and Systems, University of Tsukuba), Dai Hasegawa (College of Science and Engineering, Aoyama Gakuin University), Naoya Shioiri (Graduate School of Science and Engineering, Aoyama Gakuin University), Kouzou Ohara (College of Science and Engineering, Aoyama Gakuin University), Hiroshi Sakuta (College of Science and Engineering, Aoyama Gakuin University)

キーワード: 条件付き確率場，機械学習，ジェスチャ，擬人化エージェント　　Conditional Random Fields，Machine Learning，Gesture，Human-like Agent

要約(英語): The research field of human like agents that are often represented by an animation character is becoming increasingly active in recent years. As the motion of such agents influences the users' impression, it is easy to expect that the ability of the human like agent to make appropriate gestures could improve the understandability of the utterance contents. The load of the content creator, however, increases if he/she needs to determine when and what gestures the agent should make. This paper attempts to estimate the appropriate gestures for a given utterance text using conditional random fields (CRF), which can be used to reduce the effort spent by contents creators. We create the dataset consisting of the utterance text and the corresponding gesture labels from the educational movie contents and construct a gesture-labeling model using CRF in a supervised learning manner. The estimation performance of appearing the gestures is evaluated and compared with the simple existing model. Especially, we focus on the metaphoric gesture, often representing an abstract concept. This is because the metaphoric gesture is expected to facilitate the users' understanding of the abstract concepts. We empirically confirmed that the proposed model can distinctly estimate the metaphoric and other gestures.

本誌: 電気学会論文誌C（電子・情報・システム部門誌） Vol.136 No.3 （2016） 特集：機械学習が拓くシステムイノベーション

本誌掲載ページ: 308-317 p

原稿種別: 論文／日本語

電子版へのリンク: https://www.jstage.jst.go.jp/article/ieejeiss/136/3/136_308/_article/-char/ja/