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

Research on retriving speech and acoustic dark data

Research Project

Project/Area Number 23K24895
Project/Area Number (Other) 22H03639 (2022-2023)
Research Category

Grant-in-Aid for Scientific Research (B)

Allocation TypeMulti-year Fund (2024)
Single-year Grants (2022-2023)
Section一般
Review Section Basic Section 61030:Intelligent informatics-related
Research InstitutionKeio University (2024)
The University of Tokyo (2022-2023)

Principal Investigator

高道 慎之介  慶應義塾大学, 理工学部(矢上), 准教授 (90784330)

Co-Investigator(Kenkyū-buntansha) 井本 桂右  同志社大学, 文化情報学部, 准教授 (90802116)
猿渡 洋  東京大学, 大学院情報理工学系研究科, 教授 (30324974)
Project Period (FY) 2022-04-01 – 2026-03-31
Project Status Granted (Fiscal Year 2024)
Budget Amount *help
¥17,160,000 (Direct Cost: ¥13,200,000、Indirect Cost: ¥3,960,000)
Fiscal Year 2025: ¥3,380,000 (Direct Cost: ¥2,600,000、Indirect Cost: ¥780,000)
Fiscal Year 2024: ¥3,640,000 (Direct Cost: ¥2,800,000、Indirect Cost: ¥840,000)
Fiscal Year 2023: ¥5,070,000 (Direct Cost: ¥3,900,000、Indirect Cost: ¥1,170,000)
Fiscal Year 2022: ¥5,070,000 (Direct Cost: ¥3,900,000、Indirect Cost: ¥1,170,000)
Keywords音声認識合成 / 音響認識合成 / ダークデータ / コーパス
Outline of Research at the Start

本研究課題は,音声音響ダークデータから,超大規模かつ広範利用できる音声音響コーパスを構築する方法論を扱う.その実現にあたり,(1) 音声音響ダークデータを自動取得するWeb工学技術の開発,(2)ダークデータからその利用可能性を定量化する機械学習技術の開発,(3)大規模データに対する効率的なラベリング法,(4)種々の音声音響認識合成における評価を実施する.

Outline of Annual Research Achievements

本年度は (1) 評価ループに基づく音声合成,(2) Webデータからのコーパス構築法,(3) 音響イベントとシーンの同時分析を提案した.
(1) 評価ループに基づく音声合成については,ダークデータから音声合成を構築する方法を提案した.ダークデータに対するデータ洗練処理が機械学習にとって最適とは限らないため,最終的な機械学習性能が最大になるようにデータ洗練・選択を実行する方法を提案した.
(2) Webデータからのコーパス構築法については,動画に紐づくメタ情報を用いて,所望の音声データを構築する方法を提案した.
(3) 音響イベントとシーン同時分析においては,Webデータのようなノイジーなデータにしばしば登場する乱出データを分析する方法を提案した.

Current Status of Research Progress
Current Status of Research Progress

2: Research has progressed on the whole more than it was originally planned.

Reason

当初の予定通りに進行している.

Strategy for Future Research Activity

大規模音声音響モデル,大規模音声コーパスの頒布を進める.

Report

(2 results)
  • 2023 Annual Research Report
  • 2022 Annual Research Report
  • Research Products

    (22 results)

All 2024 2023 2022 Other

All Int'l Joint Research (1 results) Journal Article (3 results) (of which Int'l Joint Research: 1 results,  Peer Reviewed: 3 results,  Open Access: 3 results) Presentation (18 results) (of which Int'l Joint Research: 8 results,  Invited: 1 results)

  • [Int'l Joint Research] Carnegie mellon university(米国)

    • Related Report
      2023 Annual Research Report
  • [Journal Article] SelfRemaster: Self-Supervised Speech Restoration for Historical Audio Resources2024

    • Author(s)
      Takaaki Saeki , Shinnosuke Takamichi , Tomohiko Nakamura , Naoko Tanji , and Hiroshi Saruwatari
    • Journal Title

      IEEE Access

      Volume: -

    • Related Report
      2023 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Text-Inductive Graphone-Based Language Adaptation for Low-Resource Speech Synthesis2024

    • Author(s)
      Takaaki Saeki , Soumi Maiti , Xinjian Li , Shinji Watanabe , Shinnosuke Takamichi , and Hiroshi Saruwatari
    • Journal Title

      IEEE/ACM Transactions on Audio, Speech, and Language Processing

      Volume: -

    • Related Report
      2023 Annual Research Report
    • Peer Reviewed / Open Access / Int'l Joint Research
  • [Journal Article] Onoma-to-wave: Environmental Sound Synthesis from Onomatopoeic Words2022

    • Author(s)
      Yuki Okamoto, Keisuke Imoto, Shinnosuke Takamichi, Ryosuke Yamanishi, Takahiro Fukumori, and Yoichi Yamashita
    • Journal Title

      APSIPA Transactions on Signal and Information Processing

      Volume: 11 Pages: 1-20

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed / Open Access
  • [Presentation] 環境音に対する日本語自由記述文コーパスとベンチマーク分析2024

    • Author(s)
      岡本 悠希 , 高道 慎之介 , 森松 亜依 , 渡邊 亞椰 , 井本 桂右 , and 山下 洋一
    • Organizer
      言語処理学会 全国大会
    • Related Report
      2023 Annual Research Report
  • [Presentation] Coco-Nut: 自由記述文による声質制御に向けた多話者音声・声質自由記述ペアデータセット2023

    • Author(s)
      渡邊 亞椰 , 高道 慎之介 , 齋藤 佑樹 , 辛 徳泰 , and 猿渡 洋
    • Organizer
      日本音響学会秋季研究発表会
    • Related Report
      2023 Annual Research Report
  • [Presentation] Coco-Nut: Corpus of Japanese Utterance and Voice Characteristics Description for Prompt-based Control2023

    • Author(s)
      Aya Watanabe , Shinnosuke Takamichi , Yuki Saito , Wataru Nakata , Detai Xin , and Hiroshi Saruwatari
    • Organizer
      IEEE Automatic Speech Recogiton and Understanding Workshop
    • Related Report
      2023 Annual Research Report
    • Int'l Joint Research
  • [Presentation] 深層学習で獲得される音声シンボルは自然言語シンボルと同様に Zipf 則に従うか?2023

    • Author(s)
      前田 紘希 , 高道 慎之介 , 朴 浚鎔 , and 猿渡 洋
    • Organizer
      日本音響学会秋季研究発表会
    • Related Report
      2023 Annual Research Report
  • [Presentation] 学習・評価ループを用いたデータ選択によるダークデータからの音声合成2023

    • Author(s)
      関 健太郎 , 高道 慎之介 , 佐伯 高明 , and 猿渡 洋
    • Organizer
      日本音響学会春季研究発表会
    • Related Report
      2023 Annual Research Report
  • [Presentation] Visual onoma-to-wave: environmental sound synthesis from visual onomatopoeias and sound-source images2023

    • Author(s)
      Hien Ohnaka , Shinnosuke Takamichi , Keisuke Imoto , Yuki Okamoto , Kazuki Fujii , and Hiroshi Saruwatari
    • Organizer
      Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
    • Related Report
      2023 Annual Research Report
    • Int'l Joint Research
  • [Presentation] How Generative Spoken Language Model Encodes Noisy Speech: Investigation from Phonetics to Syntactics2023

    • Author(s)
      Joonyong Park , Shinnosuke Takamichi , Tomohiko Nakamura , Kentaro Seki , Detai Xin , and Hiroshi Saruwatari
    • Organizer
      Proceedings of Interspeech
    • Related Report
      2023 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Text-to-speech synthesis from dark data with evaluation-in-the-loop data selection2023

    • Author(s)
      Kentaro Seki , Shinnosuke Takamichi , Takaaki Saeki , and Hiroshi Saruwatari
    • Organizer
      Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
    • Related Report
      2023 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Joint Analysis of Acoustic Scenes and Sound Events Based on Semi-Supervised Approach2023

    • Author(s)
      Ami Igarashi, Shunsuke Tsubaki, Daisuke Niizumi, Daiki Takeuchi, Noboru Harada, and Keisuke Imoto
    • Organizer
      Proc. Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)
    • Related Report
      2023 Annual Research Report
    • Int'l Joint Research
  • [Presentation] アノテータごとのばらつきを考慮した音響イベント検出2023

    • Author(s)
      古賀 直樹, 坂東 宣昭, 井本 桂右
    • Organizer
      情報処理学会 第86回全国大会
    • Related Report
      2023 Annual Research Report
  • [Presentation] 環境音分析における事前学習済みモデルのバイアス調査2023

    • Author(s)
      井上 かほり, 井本 桂右
    • Organizer
      日本音響学会 2024年春季研究発表会
    • Related Report
      2023 Annual Research Report
  • [Presentation] 計算機による環境音の理解・解釈に向けた統合的コンペティションDCASE Challengeへの招待2023

    • Author(s)
      井本 桂右
    • Organizer
      日本音響学会 2023年春季研究発表会
    • Related Report
      2022 Annual Research Report
    • Invited
  • [Presentation] Visual onoma-to-wave:画像オノマトペと音源画像を利用した環境音合成の提案2023

    • Author(s)
      大中 緋慧
    • Organizer
      電子情報通信学会 音声研究会
    • Related Report
      2022 Annual Research Report
  • [Presentation] Visual Onoma-to-Wave: Environmental Sound Synthesis From Visual Onomatopoeias and Sound-Source Images2023

    • Author(s)
      Hien Ohnaka
    • Organizer
      Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Text-to-speech synthesis from dark data with evaluation-in-the-loop data selection2023

    • Author(s)
      Kentaro Seki
    • Organizer
      Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] 学習・評価ループを用いたデータ選択によるダークデータからの音声合成2023

    • Author(s)
      関 健太郎
    • Organizer
      日本音響学会 2023年春季研究発表会
    • Related Report
      2022 Annual Research Report
  • [Presentation] 環境音合成の入力情報に応じた主観評価手法の検討2022

    • Author(s)
      岡本 悠希
    • Organizer
      日本音響学会 2022年秋季研究発表会
    • Related Report
      2022 Annual Research Report
  • [Presentation] How Should We Evaluate Synthesized Environmental Sounds2022

    • Author(s)
      Yuki Okamoto
    • Organizer
      Proc. Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research

URL: 

Published: 2022-04-19   Modified: 2024-12-25  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi