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

Development of a barrier-free human speech recording system in environments with increased or decreased objective target sound and noise.

Research Project

Project/Area Number 20K12763
Research Category

Grant-in-Aid for Scientific Research (C)

Allocation TypeMulti-year Fund
Section一般
Review Section Basic Section 90150:Medical assistive technology-related
Research InstitutionAriake National College of Technology (2022-2023)
National Institute of Technology, Kumamoto College (2020-2021)

Principal Investigator

Ishibashi Takaaki  有明工業高等専門学校, 創造工学科, 准教授 (60455178)

Project Period (FY) 2020-04-01 – 2024-03-31
Project Status Completed (Fiscal Year 2023)
Budget Amount *help
¥4,290,000 (Direct Cost: ¥3,300,000、Indirect Cost: ¥990,000)
Fiscal Year 2022: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Fiscal Year 2021: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Fiscal Year 2020: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Keywords音声信号処理 / 雑音除去 / 目的音抽出 / 信号分離 / 信号処理 / 電子回路
Outline of Research at the Start

騒音のある環境でも障がい者や高齢者と一緒にバリアフリーで会話できるための、他者の発話音声を含む複数の雑音が存在する環境での雑音除去機器の実用化を目指す。本研究で想定する雑音環境は、雑音の開始や終了、パワーの変化、音源位置の移動があるような、一般的な室内での動的な音環境である。このような通常の環境で、特定の音声だけを強調し、それ以外の音を削除できる音声収録システムを実現する。

Outline of Final Research Achievements

A study was conducted to develop a target speech extraction device in environments where speech sounds increase or decrease. We proposed a method of target speech extraction and noise reduction by signal processing only during the period when the target speaker speech is present. Our sound source separation system was proposed for moving sound sources by using short-time frame processing. Furthermore, we proposed a method for extracting the target speech when the power of the noise is higher than that of the target speech.

Academic Significance and Societal Importance of the Research Achievements

音声を聞き取りやすくするためのデバイスの開発により、音声を聞き取りづらい障がい者や高齢者と一緒に会話できるようになる。また、スマートフォンでの音声認識や、音声による電子機器の制御においても、目的音声の抽出技術を用いることで騒音環境下での利用が期待できる。このように音声を用いたデバイスの使用状況を考えると、発話される場所と収録されるマイクロフォンの距離は数メートルよりも近いことが多く、騒音レベルや残響時間は一般家庭の室内を想定されることが多いと考えられる。そのため、これらの条件に基づいて目的話者音声を抽出する本研究は、バリアフリーのための技術やIoTに利用できる技術である。

Report

(5 results)
  • 2023 Annual Research Report   Final Research Report ( PDF )
  • 2022 Research-status Report
  • 2021 Research-status Report
  • 2020 Research-status Report
  • Research Products

    (11 results)

All 2023 2022 2021

All Journal Article (4 results) (of which Peer Reviewed: 4 results,  Open Access: 1 results) Presentation (7 results) (of which Int'l Joint Research: 4 results)

  • [Journal Article] Voice Activity Detection Based on Correlation of Joint Distribution of Observed Mixture Signals2023

    • Author(s)
      T. Ishibashi, T. Shimoda and K. Eguchi
    • Journal Title

      ICIC Express Letters, Part B: Applications

      Volume: 14 Issue: 03 Pages: 323

    • DOI

      10.24507/icicelb.14.03.323

    • ISSN
      2185-2766
    • Related Report
      2023 Annual Research Report 2022 Research-status Report
    • Peer Reviewed
  • [Journal Article] Speech Estimation Method without Sign Indetermination Based on Blind Source Separation Using Rotation2022

    • Author(s)
      T. Ishibashi and K. Eguchi
    • Journal Title

      ICIC Express Letters, Part B: Applications

      Volume: 13 Issue: 05 Pages: 471

    • DOI

      10.24507/icicelb.13.05.471

    • ISSN
      2185-2766
    • Related Report
      2022 Research-status Report
    • Peer Reviewed / Open Access
  • [Journal Article] Blind Source Separation Based on Estimation for the Number of Sources and Target Speech Selection2021

    • Author(s)
      T. Ishibashi and K. Eguchi
    • Journal Title

      ICIC Express Letters, Part B: Applications

      Volume: 12 Issue: 05 Pages: 435

    • DOI

      10.24507/icicelb.12.05.435

    • ISSN
      2185-2766
    • Related Report
      2021 Research-status Report
    • Peer Reviewed
  • [Journal Article] Blind Source Separation for Human Speeches Based on Orthogonalization of Joint Distribution of Observed Mixture Signals2021

    • Author(s)
      T. Ishibashi and K. Eguchi
    • Journal Title

      ICIC Express Letters, Part B: Applications

      Volume: 12 Issue: 05 Pages: 443

    • DOI

      10.24507/icicelb.12.05.443

    • ISSN
      2185-2766
    • Related Report
      2021 Research-status Report
    • Peer Reviewed
  • [Presentation] Voice Activity Detection and Speech Separation Using Correlation Coefficient2023

    • Author(s)
      T. Shimoda, K. Eguchi and T. Ishibashi
    • Organizer
      17th International Conference on Innovative Computing, Information and Control
    • Related Report
      2023 Annual Research Report
    • Int'l Joint Research
  • [Presentation] 騒音の大きな環境下での発話区間検出と音源分離の考察2023

    • Author(s)
      下田匠海, 石橋孝昭
    • Organizer
      第38回信号処理シンポジウム
    • Related Report
      2023 Annual Research Report
  • [Presentation] 目的話者音声の周りに存在する他人の発話音を除去するためのシステムの開発2023

    • Author(s)
      下田匠海, 石橋孝昭
    • Organizer
      日本福祉工学会第27回学術講演会
    • Related Report
      2023 Annual Research Report
  • [Presentation] Voice Activity Detection Using Correlation of Distribution of Observed Signals2022

    • Author(s)
      T. Shimoda, K. Eguchi and T. Ishibashi
    • Organizer
      16th International Conference on Innovative Computing, Information and Control
    • Related Report
      2022 Research-status Report
    • Int'l Joint Research
  • [Presentation] 強雑音環境における発話区間の推定2022

    • Author(s)
      下田匠海, 石橋孝昭
    • Organizer
      第30回電子情報通信学会九州支部学生会講演会
    • Related Report
      2022 Research-status Report
  • [Presentation] Multiple Sound Source Separation Method Using Three Microphones2022

    • Author(s)
      T. Kai, K. Kiyota, K. Eguchi and T. Ishibashi
    • Organizer
      10th IIAE International Conference on Industrial Application Engineering
    • Related Report
      2021 Research-status Report
    • Int'l Joint Research
  • [Presentation] Speech Estimation Method without Sign Indetermination Based on Blind Source Separation Using Rotation2021

    • Author(s)
      T. Ishibashi and K. Eguchi
    • Organizer
      15th International Conference on Innovative Computing, Information and Control
    • Related Report
      2021 Research-status Report
    • Int'l Joint Research

URL: 

Published: 2020-04-28   Modified: 2025-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi