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

End-to-End Model for Task-Independent Speech Understanding and Dialogue

Research Project

Project/Area Number 20H00602
Research Category

Grant-in-Aid for Scientific Research (A)

Allocation TypeSingle-year Grants
Section一般
Review Section Medium-sized Section 61:Human informatics and related fields
Research InstitutionKyoto University

Principal Investigator

Kawahara Tatsuya  京都大学, 情報学研究科, 教授 (00234104)

Co-Investigator(Kenkyū-buntansha) 井上 昂治  京都大学, 情報学研究科, 助教 (10838684)
吉井 和佳  京都大学, 情報学研究科, 准教授 (20510001)
Project Period (FY) 2020-04-01 – 2024-03-31
Project Status Completed (Fiscal Year 2023)
Budget Amount *help
¥44,720,000 (Direct Cost: ¥34,400,000、Indirect Cost: ¥10,320,000)
Fiscal Year 2023: ¥9,620,000 (Direct Cost: ¥7,400,000、Indirect Cost: ¥2,220,000)
Fiscal Year 2022: ¥12,220,000 (Direct Cost: ¥9,400,000、Indirect Cost: ¥2,820,000)
Fiscal Year 2021: ¥12,220,000 (Direct Cost: ¥9,400,000、Indirect Cost: ¥2,820,000)
Fiscal Year 2020: ¥10,660,000 (Direct Cost: ¥8,200,000、Indirect Cost: ¥2,460,000)
Keywords音声理解 / 音声対話 / 音声認識 / End-to-Endモデル
Outline of Research at the Start

人間どうしが行うような音声コミュニケーションにおいて、相手の意図・概念・感情を理解し、応答するためのモデルを研究する。音声から理解さらには相槌生成を行う系と、理解結果に応じて適切な知識・モデルを用いて応答生成を行う系のEnd-to-Endモデル化を行う。これにより、音声認識誤りの影響と音声に含まれるニュアンスや感情などの情報を考慮して、インタラクションを行うシステムを実現する。傾聴・カウンセリングや就職面接などを対象として、モデル化及び対話システムのロボットによる実装を行う。これにより、人間のコミュニケーションスキルの解明と実現を目指す。

Outline of Final Research Achievements

For general-purpose speech understanding and dialogue based on the end-to-end models, various studies were conducted from the perspective of advanced speech recognition and dialogue generation. First, we designed and implemented an end-to-end system that directly recognizes dialogue acts and emotions from speech. Next, we proposed an effective learning method for speech recognition of low-resource languages by integrating speaker, language and domain recognition. We also built a model for generating punctuated and cleaned text directly from speech. Furthermore, we studied how to integrate emotion recognition with speech and gender recognition for effective learning. With regard to dialogue generation, end-to-end models represented by the large-scale language models have become the mainstream, and we proposed a mechanism to reason the user's intention and emotion and the system's intention and emotion before response generation.

Academic Significance and Societal Importance of the Research Achievements

音声認識はend-to-endモデルを大規模なデータで学習することで、大きな性能の向上を実現したが、少資源言語の音声認識や感情認識の性能はまだ十分でない。これに対して、様々な音声の属性を統合することで、大きな改善が得られることを示した。
対話生成においても大規模言語モデルが隆盛を極めているが、ロボットなどに実装する際には意図や感情などの内部状態のモデルを構築・学習することで、共感的・共生的なシステムの実現につながることが期待される。

Report

(6 results)
  • 2023 Annual Research Report   Final Research Report ( PDF )
  • 2022 Annual Research Report
  • 2021 Annual Research Report
  • 2020 Comments on the Screening Results   Annual Research Report
  • Research Products

    (34 results)

All 2024 2023 2022 2021 2020

All Journal Article (5 results) (of which Peer Reviewed: 4 results,  Open Access: 4 results) Presentation (27 results) (of which Int'l Joint Research: 27 results) Book (2 results)

  • [Journal Article] Automatic speech recognition based on large pretrained models2023

    • Author(s)
      河原 達也、三村 正人
    • Journal Title

      THE JOURNAL OF THE ACOUSTICAL SOCIETY OF JAPAN

      Volume: 79 Issue: 9 Pages: 455-460

    • DOI

      10.20697/jasj.79.9_455

    • ISSN
      0369-4232, 2432-2040
    • Year and Date
      2023-09-01
    • Related Report
      2023 Annual Research Report
  • [Journal Article] End-to-End Generation of Written-style Transcript of Speech from Parliamentary Meetings2023

    • Author(s)
      Mimura Masato、Kawahara Tatsuya
    • Journal Title

      Journal of Natural Language Processing

      Volume: 30 Issue: 1 Pages: 88-124

    • DOI

      10.5715/jnlp.30.88

    • ISSN
      1340-7619, 2185-8314
    • Related Report
      2022 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] TriECCC: Trilingual Corpus of the Extraordinary Chambers in the Courts of Cambodia for Speech Recognition and Translation Studies2022

    • Author(s)
      Soky Kak、Mimura Masato、Kawahara Tatsuya、Chu Chenhui、Li Sheng、Ding Chenchen、Sam Sethserey
    • Journal Title

      International Journal of Asian Language Processing

      Volume: 31 Issue: 03n04 Pages: 1-21

    • DOI

      10.1142/s2717554522500072

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Synthesizing waveform sequence-to-sequence to augment training data for sequence-to-sequence speech recognition2021

    • Author(s)
      S.Ueno, M.Mimura, S.Sakai, and T.Kawahara
    • Journal Title

      Acoustical Science and Technology

      Volume: 42 Issue: 6 Pages: 333-343

    • DOI

      10.1250/ast.42.333

    • NAID

      130008110355

    • ISSN
      0369-4232, 1346-3969, 1347-5177
    • Year and Date
      2021-11-01
    • Related Report
      2021 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Alignment knowledge distillation for online streaming attention-based speech recognition2021

    • Author(s)
      H.Inaguma and T.Kawahara
    • Journal Title

      IEEE/ACM Trans. Audio, Speech & Language Process

      Volume: Vol.29 Pages: 1-15

    • DOI

      10.1109/taslp.2021.3133217

    • Related Report
      2021 Annual Research Report
    • Peer Reviewed / Open Access
  • [Presentation] Enhancing two-stage finetuning for speech emotion recognition using adapters.2024

    • Author(s)
      Y.Gao, H.Shi, C.Chu, and T.Kawahara.
    • Organizer
      IEEE-ICASSP
    • Related Report
      2023 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Reasoning before responding: Integrating commonsense-based causality explanation for empathetic response generation.2023

    • Author(s)
      Y.Fu, K.Inoue, C.Chu, and T.Kawahara.
    • Organizer
      SIGDIAL
    • Related Report
      2023 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Two-stage finetuning of wav2vec 2.0 for speech emotion recognition with ASR and gender pretraining.2023

    • Author(s)
      Y.Gao, C.Chu, and T.Kawahara.
    • Organizer
      INTERSPEECH
    • Related Report
      2023 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Embedding articulatory constraints for low-resource speech recognition based on large pre-trained model.2023

    • Author(s)
      J.Lee, M.Mimura, and T.Kawahara.
    • Organizer
      INTERSPEECH
    • Related Report
      2023 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Time-domain speech enhancement assisted by multi-resolution frequency encoder and decoder.2023

    • Author(s)
      H.Shi, M.Mimura, L.Wang, J.Dang, and T.Kawahara.
    • Organizer
      IEEE-ICASSP
    • Related Report
      2023 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Domain and language adaptation using heterogeneous datasets for wav2vec2.0-based speech recognition of low-resource language.2023

    • Author(s)
      K.Soky, S.Li, C.Chu, and T.Kawahara.
    • Organizer
      IEEE-ICASSP
    • Related Report
      2023 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Fusing multiple bandwidth spectrograms for improving speech enhancement.2022

    • Author(s)
      H.Shi, Y.Shu, L.Wang, J.Dang, and T.Kawahara.
    • Organizer
      APSIPA ASC
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Subband-based spectrogram fusion for speech enhancement by combining mapping and masking approaches.2022

    • Author(s)
      H.Shi, L.Wang, S.Li, J.Dang, and T.Kawahara.
    • Organizer
      APSIPA ASC
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Non-autoregressive error correction for CTC-based ASR with phone-conditioned masked LM.2022

    • Author(s)
      H.Futami, H.Inaguma, S.Ueno, M.Mimura, S.Sakai, and T.Kawahara.
    • Organizer
      INTERSPEECH
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] End-to-end speech-to-punctuated-text recognition.2022

    • Author(s)
      J.Nozaki, T.Kawahara, K.Ishizuka, and T.Hashimoto.
    • Organizer
      INTERSPEECH
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Leveraging simultaneous translation for enhancing transcription of low-resource language via cross attention mechanism.2022

    • Author(s)
      K.Soky, S.Li, M.Mimura, C.Chu, and T.Kawahara.
    • Organizer
      INTERSPEECH
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Monaural speech enhancement based on spectrogram decomposition for convolutional neural network-sensitive feature extraction.2022

    • Author(s)
      H.Shi, L.Wang, S.Li, J.Dang, and T.Kawahara.
    • Organizer
      INTERSPEECH
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Selective multi-task learning for speech emotion recognition using corpora of different styles.2022

    • Author(s)
      H.Zhang, M.Mimura, T.Kawahara, and K.Ishizuka.
    • Organizer
      IEEE-ICASSP
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Phone-informed refinement of synthesized mel spectrogram for data augmentation in speech recognition.2022

    • Author(s)
      S.Ueno and T.Kawahara.
    • Organizer
      IEEE-ICASSP
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] An end-to-end model from speech to clean transcript for parliamentary meetings2021

    • Author(s)
      M.Mimura, S.Sakai, and T.Kawahara
    • Organizer
      APSIPA ASC
    • Related Report
      2021 Annual Research Report
    • Int'l Joint Research
  • [Presentation] ASR rescoring and confidence estimation with ELECTRA2021

    • Author(s)
      H.Futami, H.Inaguma, M.Mimura, S.Sakai, and T.Kawahara
    • Organizer
      IEEE Workshop Automatic Speech Recognition & Understanding (ASRU)
    • Related Report
      2021 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Data augmentation for ASR using TTS via a discrete representation2021

    • Author(s)
      S.Ueno, M.Mimura, S.Sakai, and T.Kawahara
    • Organizer
      IEEE Workshop Automatic Speech Recognition & Understanding (ASRU)
    • Related Report
      2021 Annual Research Report
    • Int'l Joint Research
  • [Presentation] VAD-free streaming hybrid CTC/Attention ASR for unsegmented recording2021

    • Author(s)
      H.Inaguma, M.Mimura, and T.Kawahara
    • Organizer
      INTERSPEECH
    • Related Report
      2021 Annual Research Report
    • Int'l Joint Research
  • [Presentation] StableEmit: Selection probability discount for reducing emission latency of streaming monotonic attention ASR2021

    • Author(s)
      H.Inaguma, M.Mimura, and T.Kawahara
    • Organizer
      INTERSPEECH
    • Related Report
      2021 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Multi-referenced training for dialogue response generation2021

    • Author(s)
      T.Zhao and T.Kawahara
    • Organizer
      SIGdial Meeting Discourse & Dialogue
    • Related Report
      2021 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Response generation to out-of-database questions for example-based dialogue systems.2020

    • Author(s)
      S.Isonishi, K.Inoue, D.Lala, K.Takanashi, and T.Kawahara.
    • Organizer
      Int'l Workshop Spoken Dialogue Systems (IWSDS)
    • Related Report
      2020 Annual Research Report
    • Int'l Joint Research
  • [Presentation] End-to-end speech emotion recognition combined with acoustic-to-word ASR model.2020

    • Author(s)
      H.Feng, S.Ueno, and T.Kawahara.
    • Organizer
      INTERSPEECH
    • Related Report
      2020 Annual Research Report
    • Int'l Joint Research
  • [Presentation] End-to-end speech-to-dialog-act recognition.2020

    • Author(s)
      T.V.Dang, T.Zhao, S.Ueno, H.Inaguma, and T.Kawahara.
    • Organizer
      INTERSPEECH
    • Related Report
      2020 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Topic-relevant response generation using optimal transport for an open-domain dialog system.2020

    • Author(s)
      S.Zhang, T.Zhao, and T.Kawahara.
    • Organizer
      COLING
    • Related Report
      2020 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Distilling the knowledge of BERT for sequence-to-sequence ASR.2020

    • Author(s)
      H.Futami, H.Inaguma, S.Ueno, M.Mimura, S.Sakai, and T.Kawahara.
    • Organizer
      INTERSPEECH
    • Related Report
      2020 Annual Research Report
    • Int'l Joint Research
  • [Presentation] CTC-synchronous training for monotonic attention model.2020

    • Author(s)
      H.Inaguma, M.Mimura, and T.Kawahara.
    • Organizer
      INTERSPEECH
    • Related Report
      2020 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Enhancing monotonic multihead attention for streaming ASR.2020

    • Author(s)
      H.Inaguma, M.Mimura, and T.Kawahara.
    • Organizer
      INTERSPEECH
    • Related Report
      2020 Annual Research Report
    • Int'l Joint Research
  • [Book] 音声(下)2022

    • Author(s)
      日本音響学会、岩野 公司、河原 達也、篠田 浩一、伊藤 彰則、増村 亮、小川 哲司、駒谷 和範
    • Total Pages
      208
    • Publisher
      コロナ社
    • ISBN
      9784339013672
    • Related Report
      2022 Annual Research Report
  • [Book] 音声対話システム2022

    • Author(s)
      井上 昂治、河原 達也
    • Total Pages
      272
    • Publisher
      オーム社
    • ISBN
      9784274229541
    • Related Report
      2022 Annual Research Report

URL: 

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

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi