• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to previous page

Development of MOOC by using Pedagogical Agent

Research Project

Project/Area Number 17K18075
Research Category

Grant-in-Aid for Young Scientists (B)

Allocation TypeMulti-year Fund
Research Field Educational technology
Intelligent informatics
Research InstitutionHokkai-Gakuen University (2018-2020)
Tokyo University of Technology (2017)

Principal Investigator

Hasegawa Dai  北海学園大学, 工学部, 准教授 (30633268)

Project Period (FY) 2017-04-01 – 2021-03-31
Project Status Completed (Fiscal Year 2020)
Budget Amount *help
¥4,290,000 (Direct Cost: ¥3,300,000、Indirect Cost: ¥990,000)
Fiscal Year 2020: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
Fiscal Year 2019: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2018: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
Fiscal Year 2017: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
KeywordsPedagogical Agent / Gesture / Deep Neural Network / ジェスチャ生成 / MOOCs / ジェスチャ自動生成 / ディープニューラルネットワーク / MOOC / IDML
Outline of Final Research Achievements

In this research, The concept of learner-generated MOOC (LG-MOOC) is proposed. In LG-MOOC, a learner creates learning materials and share with other learners, and the materials are performed by a pedagogical agent. To realize the concept, there were two key technologies. The one is gesture generation method for a pedagogical agent, and the other is instructional Design markup language (IDML) to help learners create effective materials. During research term, I focused on development of gesture generation method. I created a dataset where gestures paired with speech audio. A gesture generation model, then, is constructed by Deep Neural Network with the dataset. Gestures generated by the model were perceived as natural movements. However, the meanings of speech and gesture were perceived as not very consistent.

Academic Significance and Societal Importance of the Research Achievements

本研究で作成したデータセットは、日本語話者のジェスチャが3次元データとして収録されている。日本語話者によるデータセットは貴重であり、データセットおよびジェスチャ生成のためのプログラムはgithubで公開している。また本研究ではデータドリブンアプローチによってスピーチ音声から人間のジェスチャを生成する手法を提案した。生成されたジェスチャは動作として人間らしい自然さがあり、このアプローチの可能性を示唆するものであった。この技術が実現されれば、教育エージェントのみならず、ヒューマノイドロボットなど、Human-Agent/robot Interactionへの広い応用が期待できる。

Report

(5 results)
  • 2020 Annual Research Report   Final Research Report ( PDF )
  • 2019 Research-status Report
  • 2018 Research-status Report
  • 2017 Research-status Report
  • Research Products

    (17 results)

All 2021 2019 2018 2017 Other

All Int'l Joint Research (3 results) Journal Article (5 results) (of which Int'l Joint Research: 1 results,  Peer Reviewed: 5 results,  Open Access: 1 results) Presentation (9 results) (of which Int'l Joint Research: 4 results)

  • [Int'l Joint Research] KTH Royal Institute of Technology(スウェーデン)

    • Related Report
      2020 Annual Research Report
  • [Int'l Joint Research] スウェーデン王立工科大学(スウェーデン)

    • Related Report
      2019 Research-status Report
  • [Int'l Joint Research] KTH Royal Institute of Technology(スウェーデン)

    • Related Report
      2018 Research-status Report
  • [Journal Article] Moving Fast and Slow: Analysis of Representations and Post-Processing in Speech-Driven Automatic Gesture Generation2021

    • Author(s)
      Kucherenko Taras、Hasegawa Dai、Kaneko Naoshi、Henter Gustav Eje、Kjellstr?m Hedvig
    • Journal Title

      International Journal of Human-Computer Interaction

      Volume: Latest Article Issue: 14 Pages: 1-17

    • DOI

      10.1080/10447318.2021.1883883

    • Related Report
      2020 Annual Research Report
    • Peer Reviewed / Open Access / Int'l Joint Research
  • [Journal Article] Speech-to-Gesture Generation Using Bi-Directional LSTM Network2019

    • Author(s)
      Kaneko Naoshi、Takeuchi Kenta、Hasegawa Dai、Shirakawa Shinichi、Sakuta Hiroshi、Sumi Kazuhiko
    • Journal Title

      Transactions of the Japanese Society for Artificial Intelligence

      Volume: 34 Issue: 6 Pages: C-J41_1-12

    • DOI

      10.1527/tjsai.C-J41

    • NAID

      130007740807

    • ISSN
      1346-0714, 1346-8030
    • Year and Date
      2019-11-01
    • Related Report
      2019 Research-status Report
    • Peer Reviewed
  • [Journal Article] Acceptance of Avatar Mediated Distant-Care System in the Elderly2018

    • Author(s)
      長谷川大,盛川浩志,佐久田博司,中山栄純,安彦智史
    • Journal Title

      The Transactions of Human Interface Society

      Volume: 20 Issue: 2 Pages: 163-172

    • DOI

      10.11184/his.20.2_163

    • NAID

      130006744171

    • ISSN
      1344-7262, 2186-8271
    • Year and Date
      2018-05-25
    • Related Report
      2018 Research-status Report
    • Peer Reviewed
  • [Journal Article] Pedagogical Agent の導管メタファ・ジェスチャが学習者の理解に与える効果2018

    • Author(s)
      長谷川大, 白川真一, 佐久田博司
    • Journal Title

      情報処理学会論文誌「教育とコンピュータ」

      Volume: 4 Pages: 83-92

    • NAID

      170000149325

    • Related Report
      2017 Research-status Report
    • Peer Reviewed
  • [Journal Article] Creating a Speech-Gesture Dataset for Speech-Based Automatic Gesture Generation2017

    • Author(s)
      Kenta Takeuchi, Dai Hasegawa, Hiroshi Sakuta
    • Journal Title

      Communications in Computer and Information Science (CCIS)

      Volume: 713 Pages: 353-357

    • Related Report
      2017 Research-status Report
    • Peer Reviewed
  • [Presentation] Analyzing Input and Output Representations for Speech-Driven Gesture Generation2019

    • Author(s)
      Taras Kucherenko , Dai Hasegawa , Gustav Eje Henter , Naoshi Kaneko , Hedvig Kjellstrom
    • Organizer
      International Conference on Intelligent Virtual Agents (IVA2019)
    • Related Report
      2019 Research-status Report
    • Int'l Joint Research
  • [Presentation] On the Importance of Representations for Speech-Driven Gesture Generation2019

    • Author(s)
      Taras Kucherenko , Dai Hasegawa , Naoshi Kaneko , Gustav Eje Henter , Hedvig Kjellstrom
    • Organizer
      AAMAS '19: THE 18TH INTERNATIONAL CONFERENCE ON AUTONOMOUS AGENTS AND MULTIAGENT SYSTEMS
    • Related Report
      2019 Research-status Report
    • Int'l Joint Research
  • [Presentation] アバタ媒介型見守りシステムにおけるモーションキャプチャ情報を用いた機械学習の利用2019

    • Author(s)
      小田俊平,高野保真,長谷川大,佐久田博司,尾花謙伍
    • Organizer
      情報処理学会研究報告(HCI)
    • Related Report
      2018 Research-status Report
  • [Presentation] Evaluation of Speech-to-Gesture Generation Using Bi-Directional LSTM Network2018

    • Author(s)
      Dai Hasegawa, Naoshi Kaneko, Shinichi Shirakawa, Hiroshi Sakuta, Kazuhiko Sum
    • Organizer
      18th ACM International Conference on Intelligent Virtual Agents (IVA2018)
    • Related Report
      2018 Research-status Report
    • Int'l Joint Research
  • [Presentation] 講義代行ロボットにおける双方向LSTMを用いたジェスチャ自動生成システムの性能評価2018

    • Author(s)
      日和 航大,荒木 健治,長谷川 大,芳尾 哲
    • Organizer
      2018年度人工知能学会全国大会
    • Related Report
      2018 Research-status Report
  • [Presentation] Speech-to-Gesture Generation: A Challenge in Deep Learning Approach with Bi-Directional LSTM2017

    • Author(s)
      Kenta Takeuchi, Dai Hasegawa, Shirakawa Shinichi, Naoshi Kaneko, Hiroshi Sakuta, Kazuhiko Sumi
    • Organizer
      5th International Conference on Human Agent Interaction (HAI2017)
    • Related Report
      2017 Research-status Report
    • Int'l Joint Research
  • [Presentation] ヒューマノイドロボットを用いた講義代行システムにおけるジェスチャの考察2017

    • Author(s)
      日和航大, 荒木健治, 長谷川大
    • Organizer
      平成29年度電気・情報関係学会北海道支部連合大会予稿集
    • Related Report
      2017 Research-status Report
  • [Presentation] ニューラルネットワークを用いた発話テキストに対応するジェスチャの自動生成2017

    • Author(s)
      浅川 栄一, 白川 真一, 長谷川 大
    • Organizer
      計測自動制御学会 システム・情報部門 学術講演会2017 (SSI2017)
    • Related Report
      2017 Research-status Report
  • [Presentation] Bi-directional LSTMを用いた発話に伴うジェスチャの自動生成手法の検討2017

    • Author(s)
      竹内健太,長谷川大,白川真一,金子直史,佐久田博司, 鷲見和彦
    • Organizer
      HAIシンポジウム2017
    • Related Report
      2017 Research-status Report

URL: 

Published: 2017-04-28   Modified: 2022-01-27  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi