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

Study on utterance training system for improving likability by using speech processing technology

Research Project

Project/Area Number 16H05899
Research Category

Grant-in-Aid for Young Scientists (A)

Allocation TypeSingle-year Grants
Research Field Educational technology
Research InstitutionMeiji University (2019)
University of Yamanashi (2016-2018)

Principal Investigator

Morise Masanori  明治大学, 総合数理学部, 専任准教授 (60510013)

Project Period (FY) 2016-04-01 – 2020-03-31
Project Status Completed (Fiscal Year 2019)
Budget Amount *help
¥25,480,000 (Direct Cost: ¥19,600,000、Indirect Cost: ¥5,880,000)
Fiscal Year 2019: ¥1,950,000 (Direct Cost: ¥1,500,000、Indirect Cost: ¥450,000)
Fiscal Year 2018: ¥3,640,000 (Direct Cost: ¥2,800,000、Indirect Cost: ¥840,000)
Fiscal Year 2017: ¥8,580,000 (Direct Cost: ¥6,600,000、Indirect Cost: ¥1,980,000)
Fiscal Year 2016: ¥11,310,000 (Direct Cost: ¥8,700,000、Indirect Cost: ¥2,610,000)
Keywords教育工学 / 音声情報処理 / 声質変換
Outline of Final Research Achievements

We carried out a series of studies to develop a system to measure and improve the perceived likability of speech. The experiments showed that there was an appropriate range in speed of speech and duration of pauses. In pitch and timbre, we found the speech parameters related to the perceived likability. In this study, we utilize a vocoder technology to control the pitch of speech. In the timbre, we proposed a signal processing method to control the spectral centroid, which roughly corresponds to the brightness of the speech. A subjective evaluation using the proposed method was carried out. The result suggested that it was possible to improve the likability of the input speech. We implemented a prototype of a speech-likability measurement system that incorporates these technologies and confirmed that it works in a real-world environment.

Academic Significance and Societal Importance of the Research Achievements

本研究は,音声認識のようにテキスト情報を扱うものではなく,音声に対して知覚する好感度という,被験者に依存する感性情報を扱うという挑戦的なテーマである.現在の音声認識・合成技術の性能は,すでに人間と等価な水準に達しつつあるが,このような感性情報の計測・制御に関しては,被験者に対する依存性もあるため研究事例そのものが相対的に少ない状況にある.一方,発話訓練には社会的なニーズがあり,コミュニケーションの支援技術は今後需要が増加することが期待される.本研究で得られた成果は学術的にも価値があり社会的にも還元しやすく,今後類似した研究を進める指針として役立つと考えられる.

Report

(5 results)
  • 2019 Annual Research Report   Final Research Report ( PDF )
  • 2018 Annual Research Report
  • 2017 Annual Research Report
  • 2016 Annual Research Report
  • Research Products

    (42 results)

All 2020 2019 2018 2017 2016 Other

All Journal Article (12 results) (of which Peer Reviewed: 12 results,  Open Access: 9 results,  Acknowledgement Compliant: 2 results) Presentation (23 results) (of which Int'l Joint Research: 1 results) Book (3 results) Remarks (4 results)

  • [Journal Article] Voice Conversion for Improving Perceived Likability of Uttered Speech2020

    • Author(s)
      S. Horiike and M. Morise
    • Journal Title

      IEICE Transactions on Information and Systems

      Volume: E103.D Issue: 5 Pages: 1199-1202

    • DOI

      10.1587/transinf.2019EDL8126

    • NAID

      130007839089

    • ISSN
      0916-8532, 1745-1361
    • Year and Date
      2020-05-01
    • Related Report
      2019 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Development and Evaluation of Perceptual Model for Measuring Sound Quality of Mel-Cepstrum-Modified Speech2020

    • Author(s)
      小川樹,森勢将雅
    • Journal Title

      電子情報通信学会論文誌D 情報・システム

      Volume: J103-D Issue: 4 Pages: 205-214

    • DOI

      10.14923/transinfj.2019PDP0005

    • ISSN
      1880-4535, 1881-0225
    • Year and Date
      2020-04-01
    • Related Report
      2019 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Building a database for likability evaluation of uttered speech2020

    • Author(s)
      M. Morise, F. Yokomori, and K. Ozawa
    • Journal Title

      Acoustical Science and Technology

      Volume: 41 Issue: 1 Pages: 423-424

    • DOI

      10.1250/ast.41.423

    • NAID

      130007782717

    • ISSN
      0369-4232, 1346-3969, 1347-5177
    • Year and Date
      2020-01-01
    • Related Report
      2019 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Modification of Velvet Noise for Speech Waveform Generation by Using Vocoder-Based Speech Synthesizer2019

    • Author(s)
      Morise Masanori
    • Journal Title

      IEICE Transactions on Information and Systems

      Volume: E102.D Issue: 3 Pages: 663-665

    • DOI

      10.1587/transinf.2018EDL8179

    • NAID

      130007606073

    • ISSN
      0916-8532, 1745-1361
    • Year and Date
      2019-03-01
    • Related Report
      2018 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] High-quality waveform generator from fundamental frequency, spectral envelope, and band aperiodicity,2019

    • Author(s)
      M. Morise and T. Shono
    • Journal Title

      in Proc. APSIPA ASC 2019

      Volume: - Pages: 613-617

    • DOI

      10.1109/apsipaasc47483.2019.9023206

    • Related Report
      2019 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Efficient quantization of vocoded speech parameters without degradation2019

    • Author(s)
      M. Morise and G. Miyashita
    • Journal Title

      in Proc. APSIPA ASC 2019

      Volume: - Pages: 154-158

    • DOI

      10.1109/apsipaasc47483.2019.9023279

    • Related Report
      2019 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Human-in-the-loop speech-design system and its evaluation2019

    • Author(s)
      D. Kondo and M. Morise
    • Journal Title

      in Proc. APSIPA ASC 2019

      Volume: - Pages: 608-612

    • DOI

      10.1109/apsipaasc47483.2019.9023345

    • Related Report
      2019 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Sound quality comparison among high-quality vocoders by using re-synthesized speech2018

    • Author(s)
      Masanori Morise, Yusuke Watanabe
    • Journal Title

      Acoustical Science and Technology

      Volume: 39 Issue: 3 Pages: 263-265

    • DOI

      10.1250/ast.39.263

    • NAID

      130006730841

    • ISSN
      0369-4232, 1346-3969, 1347-5177
    • Year and Date
      2018-05-01
    • Related Report
      2018 Annual Research Report 2017 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Low-dimensional representation of spectral envelope without deterioration for full-band speech analysis/synthesis system2017

    • Author(s)
      M. Morise, G. Miyashita, and K. Ozawa
    • Journal Title

      in Proc. INTERSPEECH 2017

      Volume: - Pages: 409-413

    • Related Report
      2017 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Harvest: A high-performance fundamental frequency estimator from speech signals2017

    • Author(s)
      M. Morise
    • Journal Title

      in Proc. INTERSPEECH 2017

      Volume: - Pages: 2321-2325

    • Related Report
      2017 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Acoustic Feature Analysis Focusing on Gender Difference in Likability Evaluation of Female Speech2016

    • Author(s)
      横森文哉,二宮大和,森勢将雅,田中章浩,小澤賢司
    • Journal Title

      Transactions of Japan Society of Kansei Engineering

      Volume: 15 Issue: 7 Pages: 721-729

    • DOI

      10.5057/jjske.TJSKE-D-16-00075

    • NAID

      130006902594

    • ISSN
      1884-0833, 1884-5258
    • Related Report
      2016 Annual Research Report
    • Peer Reviewed / Open Access / Acknowledgement Compliant
  • [Journal Article] D4C, a band-aperiodicity estimator for high-quality speech synthesis2016

    • Author(s)
      Masanori Morise
    • Journal Title

      Speech Communication

      Volume: 84 Pages: 57-65

    • DOI

      10.1016/j.specom.2016.09.001

    • Related Report
      2016 Annual Research Report
    • Peer Reviewed / Open Access / Acknowledgement Compliant
  • [Presentation] メルケプストラムを加工した音声の音質を評価する知覚モデルの開発2019

    • Author(s)
      小川樹
    • Organizer
      情報処理学会音楽情報科学研究会
    • Related Report
      2019 Annual Research Report
  • [Presentation] 音響特徴量と抑揚の操作が発話音声の好感度に与える影響の分析2019

    • Author(s)
      堀池梓哉
    • Organizer
      日本音響学会2019年秋季研究発表会
    • Related Report
      2019 Annual Research Report
  • [Presentation] 声を操る!―WORLD vocoder2019

    • Author(s)
      森勢将雅
    • Organizer
      日本心理学会第83回大会
    • Related Report
      2019 Annual Research Report
  • [Presentation] 音響特徴量操作による発話音声の好感度改善法の性差に着目した評価2019

    • Author(s)
      堀池梓哉,森勢将雅
    • Organizer
      日本音響学会2019年春季研究発表会
    • Related Report
      2018 Annual Research Report
  • [Presentation] 発話の好感度改善を目的とした音声加工技術の検討2018

    • Author(s)
      堀池梓哉,森勢将雅
    • Organizer
      情報処理学会音楽情報科学研究会
    • Related Report
      2018 Annual Research Report
  • [Presentation] 疲労感の演技に伴う声帯振動の変化の解析2018

    • Author(s)
      生野琢郎,森勢将雅
    • Organizer
      日本音響学会2018年秋季研究発表会
    • Related Report
      2018 Annual Research Report
  • [Presentation] 高品質音声分析合成におけるスペクトル包絡の次元圧縮と音質との関係性2018

    • Author(s)
      宮下玄太,森勢将雅
    • Organizer
      日本音響学会2018年秋季研究発表会
    • Related Report
      2018 Annual Research Report
  • [Presentation] 基本周波数とスペクトル包絡操作による音声の好感度改善法の提案2018

    • Author(s)
      堀池梓哉,森勢将雅
    • Organizer
      日本音響学会2018年秋季研究発表会
    • Related Report
      2018 Annual Research Report
  • [Presentation] Time-series evaluation of men's preferences perceived from female speech2018

    • Author(s)
      T. Shono, A. Otani, M. Morise, and K. Ozawa
    • Organizer
      in Proc. NCSP 2018
    • Related Report
      2017 Annual Research Report
    • Int'l Joint Research
  • [Presentation] 高品質音声分析合成による各パラメータのフレームシフト幅が音質に与える影響2018

    • Author(s)
      宮下玄太,森勢将雅
    • Organizer
      電子情報通信学会技術研究報告
    • Related Report
      2017 Annual Research Report
  • [Presentation] 演技発話による疲労の表現によって生じる音色変化の分析2018

    • Author(s)
      生野琢郎,森勢将雅
    • Organizer
      電子情報通信学会技術研究報告
    • Related Report
      2017 Annual Research Report
  • [Presentation] 高品質音声符号化のためのスペクトル包絡・非周期性指標量子化の知覚的影響2018

    • Author(s)
      宮下玄太,森勢将雅
    • Organizer
      電子情報通信学会技術研究報告
    • Related Report
      2017 Annual Research Report
  • [Presentation] 高品質音声符号化のための基本周波数量子化の知覚的影響2018

    • Author(s)
      宮下玄太,森勢将雅
    • Organizer
      情報処理学会第80回全国大会
    • Related Report
      2017 Annual Research Report
  • [Presentation] 音声から知覚する疲労度に対応する音響特徴量の策定2018

    • Author(s)
      生野琢郎,森勢将雅
    • Organizer
      情報処理学会第80回全国大会
    • Related Report
      2017 Annual Research Report
  • [Presentation] 声道断面積関数の変換と高域強調による発話音声のはきはき感向上手法の検討2017

    • Author(s)
      渡邊優介,森勢将雅,小澤賢司
    • Organizer
      日本音響学会2017年春季研究発表会
    • Place of Presentation
      桐蔭横浜大学(神奈川県横浜市)
    • Year and Date
      2017-03-15
    • Related Report
      2016 Annual Research Report
  • [Presentation] 高品質音声分析合成を用いた基本周波数の実時間操作インタフェースの実装2017

    • Author(s)
      渡邊優介,森勢 将雅,小澤賢司
    • Organizer
      情報処理学会音楽情報科学研究会
    • Related Report
      2017 Annual Research Report
  • [Presentation] フルバンド音声を対象とした音声分析合成システムに用いるスペクトル包絡の音質劣化のない低次元表現2017

    • Author(s)
      宮下玄太,森勢将雅,小澤賢司
    • Organizer
      情報処理学会音楽情報科学研究会
    • Related Report
      2017 Annual Research Report
  • [Presentation] 誇張した時間的揺らぎが歌声の人間性知覚に与える影響2017

    • Author(s)
      森勢将雅,豊田裕一,小澤賢司
    • Organizer
      情報処理学会音楽情報科学研究会
    • Related Report
      2017 Annual Research Report
  • [Presentation] 分析合成音を用いた音声分析合成方式の性能比較2017

    • Author(s)
      渡邊優介,森勢将雅
    • Organizer
      日本音響学会2017年秋季研究発表会
    • Related Report
      2017 Annual Research Report
  • [Presentation] フルバンド音声を対象とした品質劣化のない音声分析合成のためのフレームシフト幅の検証2017

    • Author(s)
      宮下玄太,森勢将雅
    • Organizer
      日本音響学会2017年秋季研究発表会
    • Related Report
      2017 Annual Research Report
  • [Presentation] 好感度を対象とした音声データベースの構築 -発話テキストの選定とテキストから受ける好感度の評価-2017

    • Author(s)
      森勢将雅,横森文哉,小澤賢司
    • Organizer
      日本音響学会2017年秋季研究発表会
    • Related Report
      2017 Annual Research Report
  • [Presentation] 高い雑音耐性と推定精度を両立する基本周波数推定法の提案と評価2016

    • Author(s)
      森勢将雅
    • Organizer
      電子情報通信学会技術研究報告
    • Place of Presentation
      NTT武蔵野研究開発センタ(東京都武蔵野市)
    • Year and Date
      2016-12-20
    • Related Report
      2016 Annual Research Report
  • [Presentation] 音声分析合成システムWORLDにより実時間音声合成を実現するための拡張と実装例2016

    • Author(s)
      森勢将雅
    • Organizer
      情報処理学会音楽情報科学研究会
    • Place of Presentation
      東京理科大学(千葉県野田市)
    • Year and Date
      2016-07-30
    • Related Report
      2016 Annual Research Report
  • [Book] 比較文明〈35〉特集 文明のなかに声をきく2019

    • Author(s)
      森勢将雅
    • Total Pages
      219
    • Publisher
      行人社
    • ISBN
      490597898X
    • Related Report
      2019 Annual Research Report
  • [Book] 音声分析合成2018

    • Author(s)
      森勢将雅
    • Total Pages
      256
    • Publisher
      コロナ社
    • ISBN
      9784339011371
    • Related Report
      2018 Annual Research Report
  • [Book] 人工知能学大事典2017

    • Author(s)
      人工知能学会
    • Total Pages
      1600
    • Publisher
      共立出版
    • ISBN
      9784320124202
    • Related Report
      2017 Annual Research Report
  • [Remarks] 明治大学森勢研究室

    • URL

      http://www.isc.meiji.ac.jp/~mmorise/lab/

    • Related Report
      2019 Annual Research Report
  • [Remarks] 音声分析合成システムWORLD

    • URL

      http://www.isc.meiji.ac.jp/~mmorise/world/

    • Related Report
      2019 Annual Research Report
  • [Remarks] 音声分析合成システムWORLD

    • URL

      http://www.kki.yamanashi.ac.jp/~mmorise/world/

    • Related Report
      2017 Annual Research Report
  • [Remarks] 音声分析合成システムWORLD

    • URL

      https://github.com/mmorise/World

    • Related Report
      2016 Annual Research Report

URL: 

Published: 2016-04-21   Modified: 2021-02-19  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi