Control of electronic device by voice using ultra-narrow space directional microphone

• Project/Area Number: 16K21583
• Research Category: Grant-in-Aid for Young Scientists (B)
• Allocation Type: Multi-year Fund
• Research Field: Measurement engineering; Rehabilitation science/Welfare engineering
• Research Institution: National Institute of Technology, Kumamoto College
• Principal Investigator: Ishibashi Takaaki 熊本高等専門学校, 情報通信エレクトロニクス工学科, 准教授 (60455178)
• Project Period (FY): 2016-04-01 – 2019-03-31
• Project Status: Completed (Fiscal Year 2018)
• Budget Amount: ¥3,900,000 (Direct Cost: ¥3,000,000、Indirect Cost: ¥900,000); Fiscal Year 2018: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000); Fiscal Year 2017: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000); Fiscal Year 2016: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
• Keywords: 雑音除去 / 信号処理 / 計測工学

Outline of Final Research Achievements

It aims at the practical application of the noise reduction in the high noise environment to control the electronic device by voice under a noisy environment. Assume a condition in which you want to operate the electronic device when both hands are closed with luggage or materials. A method is proposed to create a beamform for direction and distance to a target speaker using microphones attached to an electronic device. An algorithm is applied to reduce the influence of ambient noise and extract the target speaker speech originally developed in a short time processing. Assuming a user of the electric wheelchair, the control system which can operate the electric wheelchair by voice command without joystick operation was created.

Academic Significance and Societal Importance of the Research Achievements

音声による電子機器の制御の利用を考えると、屋内のプライベート空間で使用されると思われる。周囲に他人がいる屋外で、スマートフォンなどの音声認識機能を利用する人を見かけないからである。したがって、発話者とマイクロホンの距離は1mよりも近く、騒音レベルや残響時間も、室内を想定して研究を進めた。そのため、これらの条件に基づいて雑音を抑制する関数を見つける本研究は、これからのIoTに関連した技術である。

Research Products

• [Journal Article] Two-Channel Microphone System with Variable Arbitrary Directional Pattern (2018)
  • Author(s): C. Okuma, K. Hayama and T. Ishibashi
  • Journal Title: ICIC Express Letters Volume: 12 Issue: 03 Pages: 229
  • DOI: 10.24507/icicel.12.03.229
  • ISSN: 1881-803X
  • Peer Reviewed / Open Access
• [Journal Article] Target Human Speech Extraction Method Based on Silent Interval Detection (2017)
  • Author(s): T. Ishibashi, K. Higuchi and C. Okuma
  • Journal Title: ICIC Express Letters, Part B: Applications Volume: 8 Issue: 12 Pages: 1603
  • DOI: 10.24507/icicelb.08.12.1603
  • NAID: 40021412052
  • ISSN: 2185-2766
  • Peer Reviewed / Open Access
• [Journal Article] Fast Blind Source Separation and Target Human Speech Extraction Method for Acoustic Signals (2017)
  • Author(s): T. Ishibashi H. Shintani and K. Nagata
  • Journal Title: ICIC Express Letters Volume: 11 Pages: 1715-1721
  • Peer Reviewed / Open Access
• [Presentation] Blind Source Separation Based on Rotation of Joint Distribution Without Inversion of Positive and Negative Sign (2019)
  • Author(s): M. Iikawa and T. Ishibashi
  • Organizer: 7th IIAE International Conference on Industrial Application Engineering 2019
  • Int'l Joint Research
• [Presentation] Estimation for the Number of Sound Sources Using Directional Histogram of Observed Mixture Signals (2019)
  • Author(s): Y. Kawakami and T. Ishibashi
  • Organizer: 7th IIAE International Conference on Industrial Application Engineering 2019
  • Int'l Joint Research
• [Presentation] Extraction of Multiple Sound Signals using Two-Channel Microphone System with Variable Arbitrary Multi-Directional Pattern (2019)
  • Author(s): Y. Oshiro, T. Ishibashi, K. Hayama, C. Okuma and K. Eguchi
  • Organizer: 2019 RISP International Workshop on Nonlinear Circuits, Communications and Signal Processing
  • Int'l Joint Research
• [Presentation] Low Distortion Target Speech Extraction Method Using Two-Channel Microphone System (2018)
  • Author(s): T. Ishibashi, K. Inoue, C. Okuma and K. Eguchi
  • Organizer: IIAE International Conference on Intelligent Systems and Image Processing 2018
  • Int'l Joint Research
• [Presentation] Noise reduction method for multiple sound source signals and its application to two-channel microphone system (2017)
  • Author(s): T. Ishibashi, K. Higuchi, C. Okuma and K. Hayama
  • Organizer: International Conference on Industrial Application Engineering
  • Place of Presentation: 福岡県北九州市（北九州国際会議場）
  • Year and Date: 2017-03-27
  • Int'l Joint Research
• [Presentation] Target sound extraction using silent interval of human speech (2017)
  • Author(s): K. Higuchi, C. Okuma and T. Ishibashi
  • Organizer: International Symposium on Artificial Life and Robotics
  • Place of Presentation: 大分県別府市（ビーコンプラザ）
  • Year and Date: 2017-01-19
  • Int'l Joint Research
• [Presentation] Blind Source Separation and Human Speech Extraction for Three Sound Sources Using Silent Interval (2017)
  • Author(s): K. Higuchi, C. Okuma and T. Ishibashi
  • Organizer: IIAE International Conference on Intelligent Systems and Image Processing
  • Int'l Joint Research
• [Presentation] Two-Channel Microphone System with Variable Arbitrary Directional Pattern (2017)
  • Author(s): C. Okuma, K. Hayama and T. Ishibashi
  • Organizer: International Conference on Innovative Computing, Information and Control
  • Int'l Joint Research
• [Presentation] Silent Interval Detection and Target Human Speech Extraction (2017)
  • Author(s): K. Higuchi, C. Okuma and T. Ishibashi
  • Organizer: International Conference on Innovative Computing, Information and Control
  • Int'l Joint Research
• [Presentation] Blind Source Separation and Target Speech Extraction for Acoustic Signals (2017)
  • Author(s): T. Ishibashi, S. Nakao and K. Nagata
  • Organizer: International Conference on Innovative Computing, Information and Control
  • Int'l Joint Research
• [Presentation] 無音区間を利用した短時間処理による目的話者音声抽出 (2016)
  • Author(s): 樋口佳奈, 大隈千春, 石橋孝昭
  • Organizer: 電子情報系高専フォーラム
  • Place of Presentation: 熊本県合志市（熊本高等専門学校）
  • Year and Date: 2016-11-12
• [Presentation] 特定話者音声認識技術を用いた電動車椅子の制御 (2016)
  • Author(s): 川内智瑛, 石橋孝昭
  • Organizer: 電子情報通信学会九州支部学生会講演会
  • Place of Presentation: 宮崎県宮崎市（宮崎大学）
  • Year and Date: 2016-09-28
• [Presentation] 騒音の同時分布を利用した話者音声の抽出 (2016)
  • Author(s): 樋口佳奈, 大隈千春, 石橋孝昭
  • Organizer: 電子情報通信学会九州支部学生会講演会
  • Place of Presentation: 宮崎県宮崎市（宮崎大学）
  • Year and Date: 2016-09-28
• [Presentation] 観測信号の相関係数に基づく無音区間を利用した騒音環境下での話者音声抽出 (2016)
  • Author(s): 樋口佳奈, 大隈千春, 石橋孝昭
  • Organizer: 産業応用工学会全国大会
  • Place of Presentation: 京都府京都市（京都市国際交流会館）
  • Year and Date: 2016-09-11
• [Remarks] 熊本高等専門学校 教員紹介
  • URL: http://www.kumamoto-nct.ac.jp/gyouseki/1000029.html
• [Remarks] 石橋研究室 研究業績 | ユビキタスコミュニケーション研究部 熊本高等専門学校
  • URL: http://www.ubi.te.kumamoto-nct.ac.jp/ishibashi/references/