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

Study of speech signal amplitude and phase reconstructions for understanding sound environment

Research Project

Project/Area Number 19K21546
Project/Area Number (Other) 18H06482 (2018)
Research Category

Grant-in-Aid for Research Activity Start-up

Allocation TypeMulti-year Fund (2019)
Single-year Grants (2018)
Review Section 1002:Human informatics, applied informatics and related fields
Research InstitutionTokyo Metropolitan University

Principal Investigator

Wakabayashi Yukoh  首都大学東京, システムデザイン研究科, 特任助教 (80826462)

Project Period (FY) 2018-08-24 – 2020-03-31
Project Status Completed (Fiscal Year 2019)
Budget Amount *help
¥2,990,000 (Direct Cost: ¥2,300,000、Indirect Cost: ¥690,000)
Fiscal Year 2019: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Fiscal Year 2018: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Keywords位相信号処理 / 音声強調 / 雑音抑圧 / 音声区間検出 / 音声信号復元 / 位相復元 / 振幅位相関係 / 振幅復元 / 音環境理解 / 位相 / 雑音除去
Outline of Research at the Start

本研究は,雑音環境下において収録された劣化音声信号から雑音の影響を除去し,真の音声信号を復元する理論の構築とその応用を目的とする.
これまでの研究では,音声信号において重要な特徴である振幅と位相を各々異なるアプローチで分析することが一般的であった.
これに対し,申請者は音声信号の位相・振幅が満たすべき時間周波数上の挙動に関連性があることに注目し,この関連性を導入した全く新しい音声信号復元の理論構築に取り組む.

Outline of Final Research Achievements

This project tackled the challenges of clean speech reconstruction from noisy observation by using relationships between speech amplitude and phase features.
In general, previous studies have separately constructed amplitude- and phase-based noise reduction algorithms. In contrast, the principal investigator proposed new algorithm that integrates the two features and confirmed its superiority over separately-handled method. In addition, he applied the relationship to another audio signal processing such as voice activity detection and showed that new integration method achieves higher performance than only amplitude-based method.

Academic Significance and Societal Importance of the Research Achievements

本研究において得られた,雑音抑圧と音声区間検出に対する結果が示すことは以下の通りである.学術的意義としては,これまで別々に研究されてきた振幅特徴と位相特徴の関連を考慮し,統合的に取り扱うことが信号処理の性能を改善する上で重要であり,より高性能な信号処理アルゴリズムの構築に繋がることが確認できたことである.社会的意義としては,雑音抑圧や音声区間検出の高性能化に伴い,今後の情報社会において必須となる音声認識性能の向上や遠隔会話システムにおける,より円滑な会話の実現が達成できることが挙げられる.

Report

(3 results)
  • 2019 Annual Research Report   Final Research Report ( PDF )
  • 2018 Annual Research Report
  • Research Products

    (12 results)

All 2020 2019 2018

All Journal Article (2 results) (of which Open Access: 2 results) Presentation (10 results) (of which Int'l Joint Research: 3 results,  Invited: 1 results)

  • [Journal Article] Speech enhancement using harmonic-structure-based phase reconstruction2019

    • Author(s)
      Yukoh Wakabayashi
    • Journal Title

      Acoustical Science and Technology

      Volume: 40 Issue: 3 Pages: 162-169

    • DOI

      10.1250/ast.40.162

    • NAID

      130007641578

    • ISSN
      0369-4232, 1346-3969, 1347-5177
    • Year and Date
      2019-05-01
    • Related Report
      2019 Annual Research Report
    • Open Access
  • [Journal Article] Speech enhancement using harmonic-structurebased phase reconstruction2019

    • Author(s)
      若林佑幸
    • Journal Title

      THE JOURNAL OF THE ACOUSTICAL SOCIETY OF JAPAN

      Volume: 75 Issue: 3 Pages: 139-146

    • DOI

      10.20697/jasj.75.3_139

    • NAID

      130007699476

    • ISSN
      0369-4232, 2432-2040
    • Year and Date
      2019-03-01
    • Related Report
      2018 Annual Research Report
    • Open Access
  • [Presentation] 周波数方向冗長化STFTに基づく位相復元の音楽信号への適用2020

    • Author(s)
      若林佑幸,小野順貴
    • Organizer
      日本音響学会2020春季研究発表会
    • Related Report
      2019 Annual Research Report
  • [Presentation] A phase-based voice activity detection using statistical likelihood ratio of the derivative of instantaneous frequency2020

    • Author(s)
      Binh Thien Nguyen, Yukoh Wakabayashi, Takahiro Fukumori, and Takanobu Nishiura
    • Organizer
      日本音響学会2020春季研究発表会
    • Related Report
      2019 Annual Research Report
  • [Presentation] 周波数を冗長化したSTFTによる位相復元の音声強調への利用2019

    • Author(s)
      若林佑幸,小野順貴
    • Organizer
      日本音響学会2019秋季研究発表会
    • Related Report
      2019 Annual Research Report
  • [Presentation] Speech analysis using the second derivative of phase spectrum2019

    • Author(s)
      Binh Thien Nguyen, Yukoh Wakabayashi, Takahiro Fukumori, and Takanobu Nishiura
    • Organizer
      日本音響学会2019秋季研究発表会
    • Related Report
      2019 Annual Research Report
  • [Presentation] Griffin-Lim phase reconstruction using short-time Fourier transform with zero-padded frame analysis2019

    • Author(s)
      Yukoh Wakabayashi and Nobutaka Ono
    • Organizer
      APSIPA ASC 2019
    • Related Report
      2019 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Derivative of Instantaneous Frequency for Voice Activity Detection Using Phase-based Approach2019

    • Author(s)
      Binh Thien Nguyen, Yukoh Wakabayashi, Takahiro Fukumori, and Takanobu Nishiura
    • Organizer
      APSIPA ASC 2019
    • Related Report
      2019 Annual Research Report
    • Int'l Joint Research
  • [Presentation] 短時間フーリエ変換の周波数方向冗長化とその位相復元への応用2019

    • Author(s)
      若林 佑幸,小野 順貴
    • Organizer
      日本音響学会2019年春季研究発表会
    • Related Report
      2018 Annual Research Report
  • [Presentation] Maximum a posteriori estimation of spectral gain with harmonic-structure-based phase reconstruction for phase-aware speech enhancement2018

    • Author(s)
      Yukoh Wakabayashi and Nobutaka Ono
    • Organizer
      APSIPA ASC 2018
    • Related Report
      2018 Annual Research Report
    • Int'l Joint Research
  • [Presentation] 音声強調における位相復元とアレイ処理への効果2018

    • Author(s)
      若林佑幸
    • Organizer
      電子情報通信学会 応用音響研究会
    • Related Report
      2018 Annual Research Report
    • Invited
  • [Presentation] 音声強調における位相スペクトルと振幅スペクトル同時推定手法の一検討2018

    • Author(s)
      若林 佑幸,小野 順貴
    • Organizer
      日本音響学会2018年秋季研究発表会
    • Related Report
      2018 Annual Research Report

URL: 

Published: 2018-08-27   Modified: 2024-03-26  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi