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

STUDIES OF AN ADVANCED AUDITORY MODEL AND THE APPLICATION TO IMPROVE THE ROBUSTNESS OF CONTINUOUS SPEECH RECOGNITION

Research Project

Project/Area Number 10650358
Research Category

Grant-in-Aid for Scientific Research (C)

Allocation TypeSingle-year Grants
Section一般
Research Field 情報通信工学
Research InstitutionFukui University

Principal Investigator

TANIGUCHI Shuji (1999-2000)  Fukui University, Faculty of Engineering, Associate Professor, 工学部, 助教授 (70115301)

小泉 卓也 (1998)  福井大学, 工学部, 教授 (80020204)

Co-Investigator(Kenkyū-buntansha) MORI Mikio  Fukui University, Faculty of Engineering, Assistant, 工学部, 助手 (70313731)
谷口 秀次  福井大学, 工学部, 助教授 (70115301)
Project Period (FY) 1998 – 2000
Project Status Completed (Fiscal Year 2000)
Budget Amount *help
¥3,500,000 (Direct Cost: ¥3,500,000)
Fiscal Year 2000: ¥900,000 (Direct Cost: ¥900,000)
Fiscal Year 1999: ¥900,000 (Direct Cost: ¥900,000)
Fiscal Year 1998: ¥1,700,000 (Direct Cost: ¥1,700,000)
Keywordssubword / learning vector quantization / auditory model / recurrent neural network / hidden Markov model / speaker-independency / speaker adaptation / robust isolated word recognition / 連続音声認識 / サブワード境界抽出 / 不特定話者音声認識 / 雑音耐性 / サブワード境界検出 / 音声認識 / 不特定話者 / 話者依存性 / セグメンテーション / SCHMM / 連結HMM / マルチHMM
Research Abstract

Our final goal is to develop a reliable continuous speech recognition system based on a model of human auditory system. So, we have studied as follows :
(1) On the base of a subword-unit-based isolated word recognizer (VQ-SWR) with the discrete hidden Markov models (DHMMs) as a recognition tool, which we developed before, the research to improve the robustness for speakers and some environment noises have been done. As experimental results, findings can be summarized as follows :
[1] A new recognizer with the DHMMs replaced with the semi-continuous HMMs have been developed. Experimental results showed a considerable improvement of the new recognizer in speakerindependency.
[2] We have developed a new subword-unit-based isolated word recognizer incorporated a multiparty and a speaker adaptation step on the base of the VQ-SWR.This is made up of DHMMs and a learning vector quantizer (LVQ) incorporated a feedback of information on the classification of input subword which is obtained from the … More output of the LVQ.Experimental results showed that the new recognizer performance including the robustness for speaker and noise in stationary states is higher than those accomplished with the conventional recognizer VQ-SWR.
(2) To aim at achieving higher word recognition rates and higher noise robustness than the VQ-SWR, we have proposed a new recognizer (CM-RN-SWR) made up of a model (NLF-COM) of human cochlea called "a nonlinear feedback model for cochlea", a simple multi-layer recurrent neural network (RNN) which has feedback connections of self-loop type, and DHMMs for words. The NLF-COM and the RNN which were developed before by us has been used as a model of the human auditory system, and as a kind of spectrum analyzer for speech sounds and a subword recognizer, respectively. Experimental results showed that recognition accuracies for clean speech and speech in the presence of pseud-white noise are considerably improved in speaker-dependent applications in comparison with the VQ-SWR. Less

Report

(4 results)
  • 2000 Annual Research Report   Final Research Report Summary
  • 1999 Annual Research Report
  • 1998 Annual Research Report
  • Research Products

    (27 results)

All Other

All Publications (27 results)

  • [Publications] Takuya Koizumi: "Improving the Speaker-Dependency of Subword-Unit-Based Isolated Word Recognition"Proceedings of 1998 International Conference on Spoken Language Processing(ICSLP 98). 2. 345-348 (1998)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2000 Final Research Report Summary
  • [Publications] 向當一洋: "サブワード単位離散単語認識システムの話者依存性の改善"電子情報通信学会技術研究報告. SP98-47. 15-21 (1998)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2000 Final Research Report Summary
  • [Publications] 坂本英士: "単語認識システムにおけるロバストなセグメンテーション法(I)"平成11年度電気関係学会北陸支部連合大会講演論文集. 141 (1999)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2000 Final Research Report Summary
  • [Publications] 橋詰和永: "単語認識システムにおけるロバストなセグメンテーション法(II)"平成11年度電気関係学会北陸支部連合大会講演論文集. 142 (1999)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2000 Final Research Report Summary
  • [Publications] 松井宏徳: "離散単語認識システムにおける話者適応"平成11年度電気関係学会北陸支部連合大会講演論文集. 146 (1999)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2000 Final Research Report Summary
  • [Publications] 森幹男: "話者適応型単語音声認識システムの雑音耐性"電子情報通信学会技術研究報告. SP2000-32. 1-6 (2000)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2000 Final Research Report Summary
  • [Publications] 松井宏徳: "適応化法に基づく音声認識システムの雑音耐性改善"平成12年度電気関係学会北陸支部連合大会講演論文集. 454 (2000)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2000 Final Research Report Summary
  • [Publications] 上野博史: "単語認識システムにおけるセグメント境界抽出精度"平成12年度電気関係学会北陸支部連合大会講演論文集. 460 (2000)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2000 Final Research Report Summary
  • [Publications] 松井宏徳: "サブワード単位離散単語認識システムの雑音耐性"電子情報通信学会2001年総合大会講演論文集情報・システム1. 6. 189 (2001)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2000 Final Research Report Summary
  • [Publications] Takuya Koizumi, Shuji Taniguchi, and Kazuhiro Kohtoh: "Improving the Speaker-Dependency of Subword-Unit-Based Isolated Word Recognition"Proceedings of 1998 International Conference on Spoken Language Processing (ICSLP 98). 2. 345-348 (1998)

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      2000 Final Research Report Summary
  • [Publications] Kazuhiro Kohtoh, Shuji Taniguchi, and Takuya Koizumi: "Enhancing the Speaker-Independency of Subword-Unit-Based Isolated Word Recognition"Technical Report of the Institute of Electronics, Information and Communication Engineers (IEICE). SP98-47. 15-21 (1998)

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      2000 Final Research Report Summary
  • [Publications] H.Sakamoto, S.Suzuki, M.Mori, S.Taniguchi, et al.: "Robust subword segmentation method I in an isolated word recognizer"Proceedings of the 1999 Joint Conference of Hokuriku Chapters of Electrical Societies. B-50. 141 (1999)

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      2000 Final Research Report Summary
  • [Publications] K.Hashizume, S.Suzuki, M.Mori, S.Taniguchi, et al.: "Robust subword segmentation method II in an isolated word recognizer"Proceedings of the 1999 Joint Conference of Hokuriku Chapters of Electrical Societies. B-51. 142 (1999)

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      2000 Final Research Report Summary
  • [Publications] H.Matsui, S.Suzuki, M.Mori, S.Taniguchi, et al.: "A speaker adaptation method in an isolated word recognition system"Proceedings of the 1999 Joint Conference of Hokuriku Chapters of Electrical Societies. B-55. 146 (1999)

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      2000 Final Research Report Summary
  • [Publications] Mikio Mori, Shuji Taniguchi, Hideji Sakamoto, Takuya Koizumi: "Noise Robustness of Speaker Adapted Recognition System"Technical Report of the Institute of Electronics, Information and Communication Engineers. SP2000-32. 1-6 (2000)

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      2000 Final Research Report Summary
  • [Publications] H.Matsui, S.Suzuki, M.Mori, S.Taniguchi, et al.: "Improving the noise robustness using an adaptation method in an isolated word recognition system"Proceedings of the 2000 Joint Conference of Hokuriku Chapters of Electrical Societies. G-10. 454 (2000)

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      2000 Final Research Report Summary
  • [Publications] H.Ueno, S.Suzuki, M.Mori, S.Taniguchi, et al.: "Subword segmentation performance of subword-unit-based isolated word recognition system"Proceedings of the 2000 Joint Conference of Hokuriku Chapters of Electrical Societies. G-16. 460 (2000)

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      2000 Final Research Report Summary
  • [Publications] H.Matsui, T.Koizumi, S.Suzuki, M.Mori, S.Taniguchi: "Improving the Noise Robustness of Subword-Unit-Based Isolated Word Recognition System"Proceedings of the 2001 IEICE General Conference, Information and System 1. D-14-19. 189 (2001)

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      2000 Final Research Report Summary
  • [Publications] 森幹男: "話者適応型単語音声認識システムの雑音耐性"電子情報通信学会技術研究報告. SP2000. 1-6 (2000)

    • Related Report
      2000 Annual Research Report
  • [Publications] 松井宏徳: "適応化法に基づく音声認識システムの雑音耐性改善"平成12年度電気関係学会北陸支部連合大会講演論文集. 454 (2000)

    • Related Report
      2000 Annual Research Report
  • [Publications] 上野博史: "単語認識システムにおけるセグメント境界抽出精度"平成12年度電気関係学会北陸支部連合大会講演論文集. 460 (2000)

    • Related Report
      2000 Annual Research Report
  • [Publications] 松井宏徳: "サブワード単位離散単語認識システムの雑音耐性"電子情報通信学会2001年総合大会講演論文集 情報・システム1. 6. 189 (2001)

    • Related Report
      2000 Annual Research Report
  • [Publications] 坂本 英士: "単語認識システムにおけるロバストなセグメンテーション法(I)"平成11年度電気関係学会北陸支部連合大会講演論文集. 141 (1999)

    • Related Report
      1999 Annual Research Report
  • [Publications] 橋詰 和永: "単語認識システムにおけるロバストなセグメンテーション法(II)"平成11年度電気関係学会北陸支部連合大会講演論文集. 142 (1999)

    • Related Report
      1999 Annual Research Report
  • [Publications] 松井 宏徳: "離散単語認識システムにおける話者適応"平成11年度電気関係学会北陸支部連合大会講演論文集. 146 (1999)

    • Related Report
      1999 Annual Research Report
  • [Publications] Takuya Koizumi: "Improving the Speaker-Dependency of Subword-Unit-Based Isolated Word Recognition" Proceedings of 1998 International Conference on Sooken Languge Processing(ICSLP'98). 2. 345-348 (1998)

    • Related Report
      1998 Annual Research Report
  • [Publications] 小泉卓也: "サブワード単位離散単語認識システムの話者依存性の改善" 電子情報通信学会技術研究報告. SP98-47. 15-21 (1998)

    • Related Report
      1998 Annual Research Report

URL: 

Published: 1998-04-01   Modified: 2016-04-21  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi