Research of speech signal processing for privacy protection

2011 Fiscal Year Final Research Report

• Project/Area Number: 21700192
• Research Category: Grant-in-Aid for Young Scientists (B)
• Allocation Type: Single-year Grants
• Research Field: Perception information processing/Intelligent robotics
• Research Institution: Toyohashi University of Technology
• Principal Investigator: YAMAMOTO Kazumasa 豊橋技術科学大学, 大学院・工学研究科, 助教 (40324230)
• Project Period (FY): 2009 – 2011
• Keywords: 音声情報処理 / プライバシ保護 / 音声認識 / 話者認識 / 実環境 / 遠隔発話 / 音源

Research Abstract

Speech signal includes a large amount of privacy information. Removing of the information is necessary for using the general useful information included in the speech signal. We developed speech elimination/speech separation, speech recognition for voice conversion, distant speech recognition techniques as the fundamental techniques for removing the privacy information accurately.

Research Products

• [Journal Article] CENSREC-4 : An evaluation framework for distant-talking speech recognition in reverberant environ-ments (2011)
  • Author(s): Takahiro Fukumori, Takanobu Nishiura, Masato Nakayama, Yuki Denda, Norihide Kitaoka, Takeshi Yamada, Kazumasa Yamamoto, Satoru Tsuge, Masakiyo Fujimoto, Tetsuya Takiguchi, Chiyomi Miyajima, Satoshi Tamura, Tetsuji Ogawa, Shigeki Matsuda, Shingo Kuroiwa, Kazuya Takeda, Satoshi Nakamura
  • Journal Title: Acoustical Science and Technology, Technical Report Volume: Vol.32 No.5 Pages: 201-210
• [Journal Article] Au-ditory perception versus automatic estimation of location and orienta-tion of an acoustic source in a real environment (2010)
  • Author(s): Alberto Yoshihiro Nakano, Seiichi Nakagawa, Kazumasa Yamamoto
  • Journal Title: Acoustical Science and Technology Volume: Vol.31, No.5 Pages: 309-319
• [Journal Article] Speaker recognition by combining MFCC and phase information in noisy condi-tions (2010)
  • Author(s): Longbiao Wang, Kazue Minami, Kazumasa Yamamoto, Seiichi Nakagawa
  • Journal Title: IEICE Transactions on In-formation and Systems Volume: Vol.E93-D, No.9 Pages: 2397-2406
• [Journal Article] Dis-tant speech recognition using a mi-crophone array network (2010)
  • Author(s): Alberto Yoshihiro Nakano, Seiichi Nakagawa, Kazumasa Yamamoto
  • Journal Title: IEICE Transactions on Information and Systems Volume: Vol.E93-D, No.9 Pages: 2451-2462
• [Journal Article] Privacy protec-tion for speech signals (2010)
  • Author(s): Kazumasa Yamamoto, Masatoshi Tsuchiya, Seiichi Nakagawa
  • Journal Title: Procedia-Social and Behavioral Sciences Volume: Vol.2, No.1 Pages: 153-160
• [Journal Article] Privacy protection for speech in-formation (2010)
  • Author(s): Kazumasa Yamamoto, Seiichi Nakagawa
  • Journal Title: Journal of Information Assurance and Security(JIAS) Volume: Vol.5, No.1 Pages: 284-292
• [Journal Article] Automatic estimation of position and orientation of an acoustic source by a microphone array network (2009)
  • Author(s): Alberto Yoshihiro Nakano, Seiichi Nakagawa, Kazumasa Yamamoto
  • Journal Title: Journal of Acoustical Society of America Volume: Vol.126, No.6 Pages: 3084-3094
• [Presentation] 音楽重畳音声の音声認識のためのNMFによる音楽除去の高速化およびVQ手法の改善 (2012)
  • Author(s): 仲野翔一,山本一公,中川聖一
  • Organizer: 日本音響学会2012年春季研究発表会講演論文集
  • Place of Presentation: 神奈川大学
  • Year and Date: 2012-03-13
• [Presentation] 残響に頑健な遠隔発話の話者認識の検討 (2012)
  • Author(s): 嶋田晃太,山本一公,中川聖一
  • Organizer: 日本音響学会2012年春季研究発表会講演論文集
  • Place of Presentation: 神奈川大学
  • Year and Date: 2012-03-13
• [Presentation] Speaker identi-fication using pseudo pitch syn-chronized phase information in voiced sound (2011)
  • Author(s): Kohta Shimada, Kazumasa Yamamoto, Seiichi Nakagawa
  • Organizer: 2011 Asia-Pacific Signal and Information Processing Association Annual Summit and Con-ference(APSIPA ASC 2011)
  • Place of Presentation: CD-ROM, Xi' an, China
  • Year and Date: 2011-10-20
• [Presentation] 長時間位相特徴と振幅スペクトル特徴の併用による音声認識の検討 (2011)
  • Author(s): 山本一公,中川聖一
  • Organizer: 日本音響学会2011年秋季研究発表会講演論文集
  • Place of Presentation: 島根大学
  • Year and Date: 2011-09-21
• [Presentation] Speech recogni-tion in mixed sound of speech and music based on vector quantization and non-negative matrix factorization (2011)
  • Author(s): Shoichi Nakano, Kazumasa Yamamoto, Seiichi Nakagawa
  • Organizer: INTERSPEECH 2011
  • Place of Presentation: Florence, Italy
  • Year and Date: 2011-08-29
• [Presentation] NMFとVQ手法による音楽重畳音声の音声認識 (2011)
  • Author(s): 仲野翔一,山本一公,中川聖一
  • Organizer: 電子情報通信学会技術研究報告
  • Place of Presentation: 名古屋大学
  • Year and Date: 2011-06-23
• [Presentation] 有声音部の位相情報を用いた話者認識の改善 (2011)
  • Author(s): 嶋田晃太,山本一公,中川聖一
  • Organizer: 日本音響学会2011年春季研究発表会講演論文集
  • Place of Presentation: 早稲田大学
  • Year and Date: 2011-03-11
• [Presentation] NMFとVQ手法による音楽重畳音声の音楽除去と音声認識 (2011)
  • Author(s): 仲野翔一,山本一公,中川聖一
  • Organizer: 日本音響学会2011年春季研究発表会講演論文集
  • Place of Presentation: 早稲田大学
  • Year and Date: 2011-03-10
• [Presentation] Large Vocabulary Speech Recognition System : SPOJUS++ (2011)
  • Author(s): Yasuhisa Fujii, Kazumasa Yamamoto, Seiichi Nakagawa
  • Organizer: 11th WSEAS International Con-ference on MULTIMEDIA SYSTEMS & SIGNAL PROCESSING(MUSP' 11)
  • Place of Presentation: Venice, Italy
  • Year and Date: 2011-03-08
• [Presentation] Speech recogni-tion using long-term phase infor-mation (2010)
  • Author(s): Kazumasa Yamamoto, Eiichi Sueyoshi, Seiichi Nakagawa
  • Organizer: INTERSPEECH 2010
  • Place of Presentation: Makuhari, Japan
  • Year and Date: 2010-09-28
• [Presentation] 長時間分析に基づく位相情報を用いた音声認識の検討 (2010)
  • Author(s): 山本一公,末吉英一,中川聖一
  • Organizer: 電子情報通信学会技術研究報告
  • Place of Presentation: 仙台秋保温泉緑水亭
  • Year and Date: 2010-07-23
• [Presentation] Speaker identification by combining MFCC and phase information in noisy environ-ments (2010)
  • Author(s): Longbiao Wang, Kazue Minami, Kazumasa Yamamoto, Seiichi Nakagawa
  • Organizer: International Conference on Acoustics, Speech, and Signal Processing(ICASSP 2010)
  • Place of Presentation: Dallas, USA
  • Year and Date: 2010-03-16
• [Presentation] 話者認識のための位相特徴抽出法の改善 (2010)
  • Author(s): 嶋田晃夫,山本一公,中川聖一
  • Organizer: 日本音響学会2010年春季研究発表会講演論文集
  • Place of Presentation: 電気通信大学
  • Year and Date: 2010-03-09
• [Presentation] 長時間位相特徴パラメータによる音声認識の検討 (2010)
  • Author(s): 末吉英一,山本一公,中川聖一
  • Organizer: 日本音響学会2010年春季研究発表会講演論文集
  • Place of Presentation: 電気通信大学
  • Year and Date: 2010-03-08
• [Presentation] 大語彙連続音声認識システムの改善: SPOJUS++ (2010)
  • Author(s): 藤井康寿,山本一公,中川聖一
  • Organizer: 第4回音声ドキュメント処理ワークショップ講演論文集
  • Place of Presentation: 豊橋技術科学大学
  • Year and Date: 2010-02-26
• [Presentation] Privacy protec-tionfor speech signal (2009)
  • Author(s): Kazumasa Yamamoto, Masatoshi Tsuchiya, Seiichi Nakagawa
  • Organizer: International Conference on Security Camera Network, Privacy Protection and Community Safety 2009(SPC2009)
  • Place of Presentation: Kiryu, Japan
  • Year and Date: 2009-10-29
• [Presentation] Distant speech recognition using spatial information estimated by a microphone array network (2009)
  • Author(s): Alberto Yoshihiro Nakano, Seiichi Nakagawa, Kazumasa Yamamoto
  • Organizer: 日本音響学会2009年秋季研究発表会講演論文集
  • Place of Presentation: 日本大学郡山キャンパス
  • Year and Date: 2009-09-15
• [Presentation] Esti-mating the position and orientation of an acoustic source with a microphone array network (2009)
  • Author(s): Alberto Yoshihiro Nakano, Seiichi Nakagawa, Kazumasa Yamamoto
  • Organizer: Proc. INTERSPEECH2009
  • Place of Presentation: Brighton, UK
  • Year and Date: 2009-09-08
• [Presentation] Privacy protection for speech in-formation (2009)
  • Author(s): Kazumasa Yamamoto, Seiichi Nakagawa
  • Organizer: The Fifth International Conference on Information Assurance and Security(IAS2009)
  • Place of Presentation: Xi' an, China
  • Year and Date: 2009-08-19
• [Book] Information Processing and Managementof Uncertainty in Knowledge-Based Systems. Applications (2010)
  • Author(s): Kazumasa Yamamoto, Seiichi Nakagawa
  • Publisher: E. Hullermeier, R. Kruse, F. Hoffmann(Eds.)