A study on new strategy of emotion recognition in speech

• Project/Area Number: 22650032
• Research Category: Grant-in-Aid for Challenging Exploratory Research
• Allocation Type: Single-year Grants
• Research Field: Perception information processing/Intelligent robotics
• Research Institution: Japan Advanced Institute of Science and Technology
• Principal Investigator: AKAGI Masato 北陸先端科学技術大学院大学, 情報科学研究科, 教授 (20242571)
• Co-Investigator(Kenkyū-buntansha): UNOKI Masashi 北陸先端科学技術大学院大学, 情報科学研究科, 准教授 (00343187) ; MIYAUCHI Ryota 北陸先端科学技術大学院大学, 情報科学研究科, 助教 (30455852) ; LI Junfeng 中国科学院, 声学研究所, 教授 (50431466)
• Project Period (FY): 2010 – 2012
• Project Status: Completed (Fiscal Year 2012)
• Budget Amount: ¥3,320,000 (Direct Cost: ¥2,900,000、Indirect Cost: ¥420,000); Fiscal Year 2012: ¥780,000 (Direct Cost: ¥600,000、Indirect Cost: ¥180,000); Fiscal Year 2011: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000); Fiscal Year 2010: ¥1,500,000 (Direct Cost: ¥1,500,000)
• Keywords: 音声認識 / 感情音声 / 音声知覚モデル / 感情基本因子 / 対話解析

Research Abstract

This study proposed a method of emotion recognition in speech, which can estimate not only the emotion itself but the degree of each emotion from speech that plural emotions are included in. This method represents each emotion as a resultant vector of the basic factor vectors, Arousal-Valence-Dominance. As the results of applying this method with our already proposed emotion perception model to emotion recognition in speech, the mapping of speech to the emotional space is the most correspondent to human responses. In addition, the recognition accuracy is also greatly excellent at the recognition rate compared with that by GMM.

Research Products

• [Journal Article] Speech Emotion Recognition System Based on a Dimensional Approach Using a Three-Layered Model (2012)
  • Author(s): Elbarougy, R. and Akagi, M.
  • Journal Title: Proc. APSIPA2012 Volume: -
  • NAID: 120006675349
  • Peer Reviewed
• [Journal Article] Comparison of emotion perception among different cultures (2010)
  • Author(s): Dang, J., Li, A., Erickson, D., Suemitsu, A., Akagi, M., Sakuraba, K., Mienmatasu, N., and Hirose, K.
  • Journal Title: Acoust. Sci. & Tech. 31 Volume: 6 Pages: 394-402
  • NAID: 120006660647
  • Peer Reviewed
• [Journal Article] A hybrid speech emotion recognition system based on spectral and prosodic features (2010)
  • Author(s): Zhou, Y., Li, J., Sun, Y., Zhang, J., Yan, Y., and Akagi, M.
  • Journal Title: IEICE Trans. Info. & Sys. Volume: E93D (10) Pages: 2813-2821
  • NAID: 10027641285
  • Peer Reviewed
• [Journal Article] 音声に含まれる感情情報の認識 -感情空間をどのように表現するか- (2010)
  • Author(s): 赤木正人
  • Journal Title: 日本音響学会誌 Volume: 66, 8 Pages: 393-398
  • NAID: 110007681909
• [Journal Article] A hybrid speech emotion recognition system based on spectral and prosodic features (2010)
  • Author(s): Yu Zhou, Junfeng Li, Yanqing Sun, Jianping Zhang, Yonghong Yan , Masato Akagi
  • Journal Title: IEICE Trans on Information and Systems Volume: Vol.E93-D, No.10 Pages: 2813-2821
  • NAID: 10027641285
  • Peer Reviewed
• [Journal Article] Comparison of emotion perception among different cultures (2010)
  • Author(s): Dang, J., Li, A., Erickson, D., Suemitsu, A., Akagi, M., Sakuraba, K., Mienmatasu, N., Hirose, K.
  • Journal Title: Acoustic Science and Technology Volume: 31, 6 Pages: 394-402
  • NAID: 120006660647
  • Peer Reviewed
• [Journal Article] 音声に含まれる感情情報の認識-感情空間をどのように表現するか (2010)
  • Author(s): 赤木正人
  • Journal Title: 日本音響学会誌 Volume: 66, 8 Pages: 393-398
  • NAID: 110007681909
• [Presentation] Automatic Speech Emotion Recognition Using A Three Layer Model (2013)
  • Author(s): Elbarougy, R. and Akagi, M.
  • Organizer: IEICE Tech. Report
  • Place of Presentation: 大同大学,名古屋,愛知県
  • Year and Date: 2013-03-01
• [Presentation] Speech Emotion Recognition System Based on a Dimensional Approach Using a Three-Layered Model (2012)
  • Author(s): Elbarougy, R. and Akagi, M
  • Organizer: Proc.APSIPA2012 (CD-ROM)
  • Place of Presentation: Hollywood, USA
  • Year and Date: 2012-12-04
• [Presentation] Comparison of methods for emotion dimensions estimation in speech using a three-layered model (2012)
  • Author(s): Elbarougy, R. and Akagi, M.
  • Organizer: IEICE Tech. Report
  • Place of Presentation: NTT研究所,厚木,神奈川県
  • Year and Date: 2012-06-14
• [Presentation] A Three-layered model for Automatic Speech Emotion Recognition using a Dimensional Approach (2012)
  • Author(s): Elbarougy R. and Akagi, M.
  • Organizer: JSPS A3 Foresight Workshop
  • Place of Presentation: 粟津温泉,石川県小松市
  • Year and Date: 2012-02-25
• [Presentation] A Three-layered model for Automatic Speech Emotion Recognition using a Dimensional Approach (2012)
  • Author(s): Elbarougy Reda, Masato Akagi
  • Organizer: JSPS A3 Foresight Workshop, Ishikawa
  • Place of Presentation: 粟津温泉(石川県小松市)
  • Year and Date: 2012-02-25
• [Presentation] 聴覚と音研究 (2011)
  • Author(s): 赤木正人
  • Organizer: 音響学会聴覚研究会資料
  • Place of Presentation: 牛岳温泉リゾート,富山県富山市
  • Year and Date: 2011-10-02
• [Presentation] 聴覚と音研究 (2011)
  • Author(s): 赤木正人
  • Organizer: 音響学会聴覚研究会
  • Place of Presentation: 牛岳温泉リゾート(富山県富山市)(招待講演)
  • Year and Date: 2011-10-02
• [Presentation] 音声の知覚と認識 -人は脳で音声を聞く.機械は?- (2011)
  • Author(s): 赤木,羽二生
  • Organizer: 日本音響学会平成23 年春季研究発表会
  • Place of Presentation: 早稲田大学,東京
  • Year and Date: 2011-03-09
• [Presentation] 音声の知覚と認識-人は脳で音声を聞く.機械は (2011)
  • Author(s): 赤木, 羽二生
  • Organizer: 日本音響学会平成23年春季研究発表会
  • Place of Presentation: 早稲田大学(東京)(招待講演)
  • Year and Date: 2011-03-09
• [Presentation] Rule-based voice conversion derived from expressive speech perception model: How do computers sing a song joyfully? (2010)
  • Author(s): Akagi, M.
  • Organizer: Tutorial, ISCSLP2010
  • Place of Presentation: National Cheng Kung University, Tainan, Taiwan.
  • Year and Date: 2010-11-29
• [Presentation] Rule based voice conversion derived from expressive speech perception model How do computers sing a song joyfully? (2010)
  • Author(s): Akagi, M.
  • Organizer: International Symposium on Chinese Spoken Language Processing 2010
  • Place of Presentation: 成功大学(Tainan, Taiwan)(招待講演)
  • Year and Date: 2010-11-29
• [Presentation] Comparison of methods for emotion dimensions estimation in speech using a three-layered model
  • Author(s): Elbarougy, R. and Akagi, M.
  • Organizer: IEICE Tech. Report, SP2012-36
  • Place of Presentation: Atsugi
• [Presentation] Automatic Speech Emotion Recognition Using A Three Layer Model
  • Author(s): Elbarougy, R. and Akagi, M.
  • Organizer: IEICE Tech. Report, SP2012-127
  • Place of Presentation: Nagoya