Research on robust speaker verification against spoofing attacks by voice imitation

• Project/Area Number: 25330206
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Research Field: Perceptual information processing
• Research Institution: Tokyo City University
• Principal Investigator: Iwano Koji 東京都市大学, メディア情報学部, 教授 (90323823)
• Co-Investigator(Kenkyū-buntansha): 篠田 浩一 東京工業大学, 情報理工学院, 教授 (10343097)
• Project Period (FY): 2013-04-01 – 2017-03-31
• Project Status: Completed (Fiscal Year 2016)
• Budget Amount: ¥4,420,000 (Direct Cost: ¥3,400,000、Indirect Cost: ¥1,020,000); Fiscal Year 2015: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000); Fiscal Year 2014: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000); Fiscal Year 2013: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
• Keywords: 話者照合 / 模倣音声 / 詐称攻撃 / 話者認識 / 個人認証

Outline of Final Research Achievements

In this research, we experimentally analyzed the effect of spoofing attacks by voice imitation on speaker verification systems and acoustical characteristics of the imitated voice. These analyses were conducted by using our original speech data consisting of professional and non-professional impersonators' imitated voice. The analysis results show that the voice imitation by non-professional impersonators significantly increases the success rate of spoofing attacks and the higher success rate is yielded by the professional impersonator's imitation. We also proposed a method for quantitatively evaluating the quality of voice imitation. The method reveals that the professional imitator efficiently approaches his voice characteristics towards the target speaker's voice.

Research Products

• [Presentation] 話者照合におけるプロの物真似タレントの声真似攻撃の影響の分析 (2017)
  • Author(s): 堀畑拓斗，岩野公司
  • Organizer: 情報処理学会全国大会
  • Place of Presentation: 名古屋大学（愛知県）
  • Year and Date: 2017-03-16
• [Presentation] Analysis of Voice Imitation by Professional/Non-Professional Impersonators Based on Kullback-Leibler Divergence between Acoustic Models (2016)
  • Author(s): Koji Iwano, Takuto Horihata
  • Organizer: 5th Joint Meeting of Acoustical Society of America and Acoustic Society of Japan
  • Place of Presentation: ホノルル（アメリカ合衆国）
  • Year and Date: 2016-11-28
  • Int'l Joint Research
• [Presentation] 声真似攻撃に対する話者照合システムの脆弱性の分析 (2015)
  • Author(s): 曽根泰斗，岩野公司
  • Organizer: 電子情報通信学会総合大会
  • Place of Presentation: 立命館大学
  • Year and Date: 2015-03-10 – 2015-03-13
• [Presentation] 声真似が話者照合に与える影響と物真似音声の音響特徴の分析 (2015)
  • Author(s): 岩野公司，曽根泰斗，坂本香菜子
  • Organizer: 電子情報通信学会音声研究会
  • Place of Presentation: じゅうろくプラザ（岐阜市文化産業交流センター）
  • Year and Date: 2015-01-22
• [Presentation] 話者照合への影響を考慮した模倣音声の音響分析 (2014)
  • Author(s): 坂本香菜子, 岩野公司
  • Organizer: 情報処理学会第76回全国大会
  • Place of Presentation: 東京電気大学
• [Remarks] 岩野研究室ホームページ
  • URL: http://www.yc.tcu.ac.jp/~iwanolab/