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

2017 Fiscal Year Annual Research Report

Platform for multimedia data protection and practical use based on user preferences against spoofing attacks in biometric information

Research Project

Project/Area Number 15H01686
Research InstitutionNational Institute of Informatics

Principal Investigator

越前 功  国立情報学研究所, 大学共同利用機関等の部局等, 教授 (30462188)

Co-Investigator(Kenkyū-buntansha) 馬場口 登  大阪大学, 工学研究科, 教授 (30156541)
山岸 順一  国立情報学研究所, 大学共同利用機関等の部局等, 准教授 (70709352)
Project Period (FY) 2015-04-01 – 2018-03-31
Keywordsコンテンツ流通・管理 / プライバシー / セキュリティ
Outline of Annual Research Achievements

平成29年度は,[目的3]個人の意思反映となりすまし検知を実現するマルチメディア保護活用基盤の構築の3つの課題,[課題3-1]顔,声,身体情報の匿名化とエンハンスメントの基本検討,[課題3-2]送り手と受け手の意思を反映したマルチメディア情報の保護・活用手法の検討および[課題3-3]マルチメディア保護活用基盤の構築・実証実験に取り組んだ.
[課題3-1]では,歩容から個人が許可なく特定されてしまうことを防ぐため,オートエンコーダ型のニューラルネットワークにより歩容を匿名化する新たな技術を提案した.本発表は高く評価され,WIFS2017でBest paper awardを受賞した.
[課題3-2]では,CG画像と自然な画像を自動で識別するニューラルネットワークを提案し,その有効性も示しWIFS2017で発表を行った.さらに,コンピュータにより生成されたテキストと人間が作成したテキストを識別する手法を提案し,PACLING2017およびAPSIPA ASC 2017で発表を行った.
[課題3-3]では,2015年に開催した話者照合システムの生体検知精度を競ったASVSpoof2015を詳細に分析し,また,その後発表された生体検知技術も含め,声の詐称検出がどこまで向上しているかをジャーナル論文としてまとめることも行い,Impact factorが5.301と非常に高いThe Journal of Selected Topics in Signal Processing (J-STSP)に採択された.また,被写体が属するコミュニティ内外におけるプライバシポリシを埋め込んだタグ:PrivacyTagを用いて,コミュニティ内外で当該人物の顔領域を適応的に保護する手法を検討・評価した.本発表は高く評価され,IFIP I3E2017でBest paper awardを受賞した.

Research Progress Status

29年度が最終年度であるため、記入しない。

Strategy for Future Research Activity

29年度が最終年度であるため、記入しない。

  • Research Products

    (26 results)

All 2018 2017

All Journal Article (5 results) (of which Peer Reviewed: 5 results) Presentation (21 results) (of which Int'l Joint Research: 19 results)

  • [Journal Article] Investigating very deep highway networks for parametric speech synthesis2018

    • Author(s)
      Wang Xin、Takaki Shinji、Yamagishi Junichi
    • Journal Title

      Speech Communication

      Volume: 96 Pages: 1~9

    • DOI

      https://doi.org/10.1016/j.specom.2017.11.002

    • Peer Reviewed
  • [Journal Article] 難視性パターンによる模様への情報埋め込み手法の検討2018

    • Author(s)
      富田 若南、野口 直哉、金田 北洋、岩村 惠市、越前 功
    • Journal Title

      電気学会論文誌. C

      Volume: 138 Pages: 435~440

    • DOI

      https://doi.org/10.1541/ieejeiss.138.435

    • Peer Reviewed
  • [Journal Article] ASVspoof: The Automatic Speaker Verification Spoofing and Countermeasures Challenge2017

    • Author(s)
      Wu Zhizheng、Yamagishi Junichi、Kinnunen Tomi、Hanilci Cemal、Sahidullah Mohammed、Sizov Aleksandr、Evans Nicholas、Todisco Massimiliano、Delgado Hector
    • Journal Title

      IEEE Journal of Selected Topics in Signal Processing

      Volume: 11 Pages: 588~604

    • DOI

      https://doi.org/10.1109/JSTSP.2017.2671435

    • Peer Reviewed
  • [Journal Article] Introduction to the Issue on Spoofing and Countermeasures for Automatic Speaker Verification2017

    • Author(s)
      Yamagishi Junichi、Kinnunen Tomi H.、Evans Nicholas、Leon Phillip De、Trancoso Isabel
    • Journal Title

      IEEE Journal of Selected Topics in Signal Processing

      Volume: 11 Pages: 585~587

    • DOI

      https://doi.org/10.1109/JSTSP.2017.2698143

    • Peer Reviewed
  • [Journal Article] Reversible Audio Information Hiding for Tampering Detection and Localization Using Sample Scanning Method2017

    • Author(s)
      X. Huang, N. Ono, A. Nishimura, I. Echizen
    • Journal Title

      Journal of Information Processing (JIP), vol. 58

      Volume: 7 Pages: 469~476

    • DOI

      https://doi.org/10.2197/ipsjjip.25.469

    • Peer Reviewed
  • [Presentation] 映像中の歩容情報保護を目的とした匿名歩容シルエットの生成2018

    • Author(s)
      廣瀬雄基, 中村和晃, 新田直子, 馬場口登
    • Organizer
      2018年電子情報通信学会総合大会
  • [Presentation] A COMPARISON OF RECENT WAVEFORM GENERATION AND ACOUSTIC MODELING METHODS FOR NEURAL-NETWORK-BASED SPEECH SYNTHESIS2018

    • Author(s)
      Xin Wang, Jaime Lorenzo-Trueba, Shinji Takaki, Lauri Juvela, Junichi Yamagishi
    • Organizer
      Proc. ICASSP 2018
    • Int'l Joint Research
  • [Presentation] HIGH-QUALITY NONPARALLEL VOICE CONVERSION BASED ON CYCLE-CONSISTENT ADVERSARIAL NETWORK2018

    • Author(s)
      Fuming Fang, Junichi Yamagishi, Isao Echizen, Jaime Lorenzo-Trueba
    • Organizer
      Proc. ICASSP 2018
    • Int'l Joint Research
  • [Presentation] The Voice Conversion Challenge 2018: Promoting Development of Parallel and Nonparallel Methods2018

    • Author(s)
      Jaime Lorenzo-Trueba, Junichi Yamagishi, Tomoki Toda, Daisuke Saito, Fernando Villavicencio, Tomi Kinnunen and Zhenhua Ling
    • Organizer
      Proc. Odyssey 2018
    • Int'l Joint Research
  • [Presentation] Can we steal your vocal identity from the Internet?: Initial investigation of cloning Obama’s voice using GAN, WaveNet and low-quality found data2018

    • Author(s)
      Jaime Lorenzo-Trueba, Fuming Fang, Xin Wang, Isao Echizen, Junichi Yamagishi and Tomi Kinnunen
    • Organizer
      Proc. Odyssey 2018
    • Int'l Joint Research
  • [Presentation] ASVspoof 2017 Version 2.0: meta-data analysis and baseline enhancements2018

    • Author(s)
      H´ector Delgado, Massimiliano Todisco, Md Sahidullah, Nicholas Evans, Tomi Kinnunen, Kong Aik Lee and Junichi Yamagishi
    • Organizer
      Proc. Odyssey 2018
    • Int'l Joint Research
  • [Presentation] A Spoofing Benchmark for the 2018 Voice Conversion Challenge: Leveraging from Spoofing Countermeasures for Speech Artifact Assessment2018

    • Author(s)
      Tomi Kinnunen, Jaime Lorenzo-Trueba, Junichi Yamagishi, Tomoki Toda, Daisuke Saito, Fernando Villavicencio and Zhenhua Ling
    • Organizer
      Proc. Odyssey 2018
    • Int'l Joint Research
  • [Presentation] t-DCF: a Detection Cost Function for the Tandem Assessment of Spoofing Countermeasures and Automatic Speaker Verification2018

    • Author(s)
      Tomi Kinnunen, Kong Aik Lee, Héctor Delgado, Nicholas Evans, Massimiliano Todisco, Md Sahidullah, Junichi Yamagishi and Douglas A. Reynolds
    • Organizer
      Proc. Odyssey 2018
    • Int'l Joint Research
  • [Presentation] Transformation on Computer-Generated Facial Image to Avoid Detection by Spoofing Detector2018

    • Author(s)
      Huy H. Nguyen, T.Ngoc-Dung Tieu, Hoang-Quoc Nguyen-Son, Junichi Yamagishi, Isao Echizen
    • Organizer
      Proc. ICME 2018
    • Int'l Joint Research
  • [Presentation] Autoregressive neural F0 model for statistical parametric speech synthesis2018

    • Author(s)
      Xin Wang, Shinji Takaki, Junichi Yamagishi
    • Organizer
      IEEE/ACM Transactions on Audio, Speech and Language Processing
    • Int'l Joint Research
  • [Presentation] Modular Convolutional Neural Network for Discriminating between Computer-Generated Images and Photographic Images2018

    • Author(s)
      Hong-Huy Nguyen, Ngoc-Dung Tieu-Thi, Hoang-Quoc Nguyen-Son, Vincent Nozick, Junichi Yamagishi and Isao Echizen
    • Organizer
      Proc. ARES 2018
    • Int'l Joint Research
  • [Presentation] 歩容シルエットクローン識別のための輪郭特徴量の検討2017

    • Author(s)
      生野祐輝, 中村和晃, 新田直子, 馬場口登
    • Organizer
      第20回画像の認識・理解シンポジウム (MIRU 2017)
  • [Presentation] The ASVspoof 2017 Challenge: Assessing the Limits of Replay Spoofing Attack Detection2017

    • Author(s)
      Tomi Kinnunen, Md Sahidullah, Hector Delgado, Massimiliano Todisco, Nicholas Evans, Junichi Yamagishi, Kong Aik Lee
    • Organizer
      Proc. Interspeech 2017
    • Int'l Joint Research
  • [Presentation] Complex-valued restricted Boltzmann machine for direct learning of frequency spectra2017

    • Author(s)
      Toru Nakashika, Shinji Takaki, Junichi Yamagishi
    • Organizer
      Proc. Interspeech 2017
    • Int'l Joint Research
  • [Presentation] Direct modeling of frequency spectra and waveform generationbased on phase recovery for DNN-based speech synthesis2017

    • Author(s)
      Shinji Takaki, Hirokazu Kameoka, Junichi Yamagishi
    • Organizer
      Proc. Interspeech 2017
    • Int'l Joint Research
  • [Presentation] An RNN-based Quantized F0 Model with Multi-tier Feedback Links forText-to-Speech Synthesis2017

    • Author(s)
      Xin Wang, Shinji Takaki, Junichi Yamagishi
    • Organizer
      Proc. Interspeech 2017
    • Int'l Joint Research
  • [Presentation] An Approach for Gait Anonymization Using Deep Learning2017

    • Author(s)
      T.Ngoc-Dung Tieu, Huy H. Nguyen, Hoang-Quoc Nguyen-Son, Junichi Yamagishi, Isao Echizen
    • Organizer
      Proc. 9th IEEE International Workshop on Information Forensics and Security (WIFS)
    • Int'l Joint Research
  • [Presentation] Identifying Computer-Generated Text Using Statistical Analysis2017

    • Author(s)
      Hoang-Quoc Nguyen-Son, Tieu Thi Ngoc Dung, Huy H. Nguyen, Junichi Yamagishi and Isao Echizen
    • Organizer
      Proc. APSIPA ASC 2017
    • Int'l Joint Research
  • [Presentation] Detecting Computer-Generated Text Using Fluency and Noise Features2017

    • Author(s)
      H.-Q. Nguyen-Son and I. Echizen
    • Organizer
      Proc. of the 2017 Conference of the Pacific Association for Computational Linguistics (Pacling2017)
    • Int'l Joint Research
  • [Presentation] PrivacyTag: A Community-based Method for Protecting Privacy of Photographed Subjects in Online Social Networks2017

    • Author(s)
      S. Machida, A. Dabrowski, E. Weippl, and Isao Echizen
    • Organizer
      Proc. of , The 16th IFIP Conference on e-Business, e-Services and e-Society (I3E2017)
    • Int'l Joint Research
  • [Presentation] Distinguishing Computer Graphics from Natural Images Using Convolution Neural Networks2017

    • Author(s)
      N. Rahmouni, V. Nozick, J. Yamagishi, and I. Echizen
    • Organizer
      Proc of the 9th IEEE International Workshop on Information Forensics and Security 2017 (WIFS2017)
    • Int'l Joint Research

URL: 

Published: 2018-12-17  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi