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

Research for Japanese Dictation System

Research Project

Project/Area Number 08680399
Research Category

Grant-in-Aid for Scientific Research (C)

Allocation TypeSingle-year Grants
Section一般
Research Field Intelligent informatics
Research InstitutionNara Institute of Science and Technology

Principal Investigator

SHIKANO Kiyohiro  Graduate School of Information Science, Nara Institute of Science and Technology, Professor, 情報科学研究科, 教授 (00263426)

Co-Investigator(Kenkyū-buntansha) NAKAMURA Satoshi  Graduate School of Information Science, Nara Institute of Science and Technology, 情報科学研究科, 助教授 (30263429)
Project Period (FY) 1996 – 1997
Project Status Completed (Fiscal Year 1997)
Budget Amount *help
¥2,400,000 (Direct Cost: ¥2,400,000)
Fiscal Year 1997: ¥1,100,000 (Direct Cost: ¥1,100,000)
Fiscal Year 1996: ¥1,300,000 (Direct Cost: ¥1,300,000)
KeywordsDictation / HMM pheneme model / language model / Continuous Speech Recognition / 音声認識 / ディクテーションシステム / 音声データベース
Research Abstract

Dictation is one of the final goal of speech recognition. In USA and EU,there have been researched in the speech recognition projects supported by the governments, such like ARPA and ESPRIT.To catch up with these projects, we had organized "Large-Vocabulary Continuous Speech Recongnition Database WG". The WG made it possible to collect a large ammount of speech database for the newspaper articles by the collaboration with many industrial research laboratories and universities.
The WG activity has been extended to the IPA project for Japanese dictation software development. This grant-aid for scientific research not only promoted the research activities in the investigater's laboratory, but also helped to organize the IPA nation-wide dictation project. The IPA dictation project shows 92% word accuracy for the 5,000-word newspaper article task. The developed acoustic models, language models and recognition program becomes the Japanese performance targets for speech recognition research and development.

Report

(3 results)
  • 1997 Annual Research Report   Final Research Report Summary
  • 1996 Annual Research Report
  • Research Products

    (54 results)

All Other

All Publications (54 results)

  • [Publications] Alexander Cirardi, Harold Singer, Kiyohiro Shikano, Satoshi Nakamura: "Maximum Likelihood Successive State Splitting Algorithm for Tied-Mixture HMNET" EUROSPEECH97. 119-122 (1997)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      1997 Final Research Report Summary
  • [Publications] 小林、鹿野: "アメリカの音声コーパス" 音声データベース、人文学と情報処理. No.12. 86-87 (1996)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      1997 Final Research Report Summary
  • [Publications] 武田、伊藤、松岡、竹沢、鹿野: "″大語彙連続音声認識研究のためのテキストデータの整備″" 情報処理学会音声言語情報処理研究会. 96-SLP-11-9. 49-54 (1996)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      1997 Final Research Report Summary
  • [Publications] 鹿野、丸山、宇津呂、松岡、竹沢: "パネル討論:統計的言語処理/音声言語処理における大規模言語データベースの利用" 情報処理学会音声言語情報処理研究会. 96-SLP-11-10. 55-60 (1996)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      1997 Final Research Report Summary
  • [Publications] 河原, 李, 伊藤, 伊藤, 宇津呂, 小林, 清水, 田本, 荒井, 峯松, 山本, 竹沢, 武田, 松岡, 鹿野: "大語彙日本語連続音声認識研究基盤の整備-評価用連続音声認識プログラムの開発" 情報処理学会音声言語情報処理研究会. 1-6 (1997)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      1997 Final Research Report Summary
  • [Publications] 伊藤, 伊藤, 宇津呂, 河原, 小林, 清水, 田本, 荒井, 峯松, 山本, 竹沢, 武田, 松岡, 鹿野: "大語彙日本語連続音声認識研究基盤の整備-学習・評価用テキストコーパスの作成" 情報処理学会音声言語情報処理研究会. 7-12 (1997)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      1997 Final Research Report Summary
  • [Publications] 武田, 伊藤, 宇津呂, 河原, 小林, 清水, 田本, 荒井, 峯松, 山本, 竹沢, 松岡, 鹿野: "大語彙日本語連続音声認識研究基盤の整備・汎用音素モデルの作成" 情報処理学会音声言語情報処理研究会. 13-18 (1997)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      1997 Final Research Report Summary
  • [Publications] 伊藤、松岡、竹沢、武田、鹿野: "大語彙連続音声認識研究のためのテキストデータ処理" 日本音響学会研究発表講演論文集. 105-106 (1996)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      1997 Final Research Report Summary
  • [Publications] 伊藤、武田、竹沢、松岡、鹿野: "大語彙連続音声認識のための読み上げ文コーパスの構築" 情報処理学会全国大会. 225-226 (1997)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      1997 Final Research Report Summary
  • [Publications] 伊藤、武田、竹沢、松岡、鹿野: "大語彙連続音声認識のための読み上げ文の選択" 日本音響学会研究発表講演論文集. 153-154 (1997)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      1997 Final Research Report Summary
  • [Publications] A.Girardi, H.Singer K.Shikoro, S.Nakamura: "Maximum likelihood sucessive state splitting algorithm for tied mixutre HM net" 日本音響学会研究発表講演論文集. 89-90 (1997)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      1997 Final Research Report Summary
  • [Publications] K.Shikano,: "Activity of Large Vocabulary Continuous Speech Database Working Group" Oriental COCOSDA Preparatory Meeting. (1997)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      1997 Final Research Report Summary
  • [Publications] 踊堂、中村、鹿野、伊藤: "連続音声認識用言語モデルに及ぼす形態素解析システムの影響" 日本音響学会研究発表講演論文集. 53-54 (1997)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      1997 Final Research Report Summary
  • [Publications] 伊藤、田中、山本、踊堂、鹿野: "音声認識用統計的言語モデルのための形態素解析済みテキストの後処理" 日本音響学会研究発表講演論文集. 27-28 (1998)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      1997 Final Research Report Summary
  • [Publications] 踊堂、中村、鹿野: "情報量に基づくtrigramモデルの圧縮" 日本音響学会研究発表講演論文集. 37-38 (1998)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      1997 Final Research Report Summary
  • [Publications] ジラルジ、シンガー、鹿野、中村: "Fast Tied-Mixture Successive State Splitting Algorithm" 日本音響学会研究発表講演論文集. 77-78 (1998)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      1997 Final Research Report Summary
  • [Publications] 北 研二、中村 哲、永田 昌明: "音声言語処理一コーパスに基づくアプローチ" 森北出版, (1996)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      1997 Final Research Report Summary
  • [Publications] 鹿野、中村、伊勢: "音声・音情報のディジタル信号処理" 昭晃堂, (1997)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      1997 Final Research Report Summary
  • [Publications] Alexander Girardi, Harald Singer, Kiyohiro Shikano, Satoshi Nakamura: "Maximum Likelihood Successive State Splitting Algorithm for Tied-Mixture HMNET" EUROSPEECH97. 119-122 (1997)

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      1997 Final Research Report Summary
  • [Publications] T.Kobayashi, K.Shikano: "Speech Corpus in U.S.A." Bensei Publisher. No.12. 86-87 (1996)

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      1997 Final Research Report Summary
  • [Publications] K.TAKEDA,K.ITO,T.MATSUOKA,T.KAKEZAWA,K.SHIKANO: "Developing Text Database for Large Vocaburary Continuous Speech Recognition Technologies" IPSJ SIG-SLP. 96-SLP-11-9. (1996)

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      1997 Final Research Report Summary
  • [Publications] K.Shikano, H.Maruyama, T.Utsuro, T.Matsuoka, T.Takezawa: "Pannel Discussion - Utilization of Large-Scale Text Database for Statistical Language Processing and Speech Processing" IPSJ SIG-SLP. 96-SLP-11-10. (1996)

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      1997 Final Research Report Summary
  • [Publications] T.Kawahara, A.Lee, K.Itou, T.Kobayashi, A.Ito, T.Utsuro, T.Shimizu, M.Tamoto, K.Arai, N.Minematsu, M.Yamamoto, T.Takezawa, K.Takeda, T.Matsuoka, K.Shikano: "Common Platform of Japanese Large Vocabulary Continuous Speech Recognition Research, - Speech Recognizer Design -" IPSJ SIG-SLP. 97-SLP-18-1. (1997)

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      1997 Final Research Report Summary
  • [Publications] K.Itou, A.Ito, T.Utsuro, T.Kawahara, T.Kobayashi, T.Shimizu, M.Tamoto, K.Arai, N.Minematsu, M.Yamamoto, T.Takezawa, K.Takeda, T.Matsuoka, K.Shikano: "Common Platform of Japanese Large Vocabulary Continuous Speech Recognition Research, - Development of Text Corpus -" IPSJ SIG-SLP. 97-SLP-18-2. (1997)

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      1997 Final Research Report Summary
  • [Publications] K.Takeda, A.Ito, K.Itou, T.Utsuro, T.Kawahara, T.Kobayashi, T.Shimizu, M.Tamoto, K.Arai, N.Minematsu, M.Yamamoto, T.Takezawa, T.Matsuoka, K.Shikano: "Common Platform of Japanese Large Vocabulary Continuous Speech Recognition Research, - Construction of Acoustic Model -" IPSJ SIG-SLP. 97-SLP-18-3. (1997)

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      1997 Final Research Report Summary
  • [Publications] Katsunobu ITO,Tastsuo MATSUOKA,Toshiyuki TAKEZAWA,Kazuya TAKEDA,Kiyohiro SHIKANo: "Japanese Text Proceeding for Large Vocaburary Continuous Speech Recognition" Acoustic Scoeity of Japan Fall Meeting. 3-3-10. 105-106 (1996)

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      1997 Final Research Report Summary
  • [Publications] Katsunobu ITO,Kazuya TAKEDA,Toshiyuki TAKEZAWA,Tatsuo MATSUOKA,Kiyohiro SHIKANO: "Development of a sentence corpus for Large Vocaburary Continuous Speech Recognition" IPSJ 54th Spring Meeting. 2-225-226. (1997)

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      1997 Final Research Report Summary
  • [Publications] Katsunobu ITO,Kazuya TAKEDA,Toshiyuki TAKEZAWA,Tatsuo MATSUOKA,Kiyohiro SHIKANO: "Sentence Selection for a sentence corpus for Large Vocaburary Continuous Speech Recognition" Acoustic Society of Japan Spring Meeting. 2-Q-7. 153-154 (1997)

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      1997 Final Research Report Summary
  • [Publications] A.Girardi, H.Singer, K.Shikano, S.Nakamura: "Maximum likelihood successive state splitting algorithm for tied mixture HMnet" Acoustic Society of Japan Spring Meeting. 3-6-1. 89-90 (1997)

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      1997 Final Research Report Summary
  • [Publications] K.Shikano: "Activity of Large Vocabulary Continuous Speech Database Working Group" Orienta COCOSDA Preparatory Meeting, Hong Kong University. (1997)

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      1997 Final Research Report Summary
  • [Publications] N.Yodo, K.ITO,S.Nakamura, K.Shikano: "The Influence of Morpheme Analysis System on Language Model for Continuous Speech Recognition" Acoustic Society of Japan Fall Meeting. 2-1-3. 53-54 (1997)

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      1997 Final Research Report Summary
  • [Publications] K.ITOU,K.TANAKA,S.YAMAMOTO,N.YODO,K.SHIKANO: "Postprocessing of Morphological Analized Text for Statistical Language Model Training in LVCSR" Acoustic Society of Japan Spring Meeting. 1-6-12. 27-28 (1998)

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      1997 Final Research Report Summary
  • [Publications] N.Yodo, S.Nakamura, K.Shikano: "Trigram size reduction based on Information Theory" Acoustic Society of Japan Spring Meeting. 1-6-17. 37-38 (1998)

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      1997 Final Research Report Summary
  • [Publications] G.Girardi, H.Singer, K.Shikano, S.Nakamura: "Fast Tied-Mixture Successive State Splitting Algorithm" Acoustic Society of Japan Spring Meeting. 2-6-12. 77-78 (1998)

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      1997 Final Research Report Summary
  • [Publications] Kenji Kita, Satoshi Nakamura, Masaaki Nagata: Speech and Language Processing - Corpus-Based Approach -. Morikita Publisher, (1996)

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      1997 Final Research Report Summary
  • [Publications] Kiyohiro Shikano, Satoshi Nakamura, Shiro Ise: Speech and Acustic Signal Digital Processing. Shoukoudou Publisher, (1997)

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      1997 Final Research Report Summary
  • [Publications] Alexander Girardi, Harold Singer, Kiyohiro Shikano, Satoshi Nakamura: ""Maximum Likelihood Successive State Splitting Algorithm for Tied-Mixture HMNET"" EUROSPEECH97. 119-122 (1997)

    • Related Report
      1997 Annual Research Report
  • [Publications] 河原, 李, 伊藤, 伊藤, 宇津呂, 小林, 清水, 田本, 荒井, 峯松, 山本, 竹沢, 武田, 松岡, 鹿野: ""大語彙日本語連続音声認識研究基盤の整備-評価用連続音声認識プログラムの開発"" 情報処理学会 音声言語情報処理研究会. 1-6 (1997)

    • Related Report
      1997 Annual Research Report
  • [Publications] 伊藤, 伊藤, 宇津呂, 河原, 小林, 清水, 田本, 荒井, 峯松, 山本, 竹沢, 武田, 松岡, 鹿野: ""大語彙日本語連続音声認識研究基盤の整備-学習・評価用テキストコーパスの作成"" 情報処理学会 音声言語情報処理研究会. 7-12 (1997)

    • Related Report
      1997 Annual Research Report
  • [Publications] 武田, 伊藤, 宇津呂, 河原, 小林, 清水, 田本, 荒井, 峯松, 山本, 竹沢, 松岡, 鹿野: ""大語彙日本語連続音声認識研究基盤の整備-汎用音素モデルの作成"" 情報処理学会 音声言語情報処理研究会. 13-18 (1997)

    • Related Report
      1997 Annual Research Report
  • [Publications] A.Girardi, H.Singer, K.Shikono, S.Nakamura: ""Maximum likelihood successive state splitting algorithm for tied mixutre HMnet"" 日本音響学会研究発表講演論文集. 89-90 (1997)

    • Related Report
      1997 Annual Research Report
  • [Publications] 踊堂, 中村, 鹿野, 伊藤: ""連続音声認識用言語モデルに及ぼす形態素解析システムの影響"" 日本音響学会研究発表講演論文集. 53-54 (1997)

    • Related Report
      1997 Annual Research Report
  • [Publications] 伊藤, 田中, 山本, 踊堂, 鹿野: ""音声認識用統計的言語モデルのための形態素解析済みテキストの後処理"" 日本音響学会研究発表講演論文集. 27-28 (1998)

    • Related Report
      1997 Annual Research Report
  • [Publications] 踊堂, 中村, 鹿野: ""情報量に基づくtrigramモデルの圧縮"" 日本音響学会研究発表講演論文集. 37-38 (1998)

    • Related Report
      1997 Annual Research Report
  • [Publications] ジラルジ, シンガー, 鹿野, 中村: ""Fast Tied-Mixture Successive State Splitting Algorithm"" 日本音響学会研究発表講演論文集. 77-78 (1998)

    • Related Report
      1997 Annual Research Report
  • [Publications] 鹿野, 中村, 伊勢: ""音声・音情報のディジタル信号処理"" 昭晃堂, (1997)

    • Related Report
      1997 Annual Research Report
  • [Publications] 武田 一哉: "大語彙連続音声認識研究のためのテキストデータの整備" 情報処理学会音声言語情報処理研究会. 96-SLP-11-9. (1996)

    • Related Report
      1996 Annual Research Report
  • [Publications] 鹿野 清宏: "統計的言語処理/音声言語処理における大規模言語データベースの利用" 情報処理学会音声言語情報処理研究会. 96-SLP-11-10. (1996)

    • Related Report
      1996 Annual Research Report
  • [Publications] 伊藤 克亘: "大語彙連続音声認識研究のためのテキストデータ処理" 日本音響学会研究発表講演論文集. 3-3-10. 105-106 (1996)

    • Related Report
      1996 Annual Research Report
  • [Publications] 伊藤 克亘: "大語彙連続音声認識のための読み上げ文コーパスの構築" 情報処理学会全国大会. 2-225. (1997)

    • Related Report
      1996 Annual Research Report
  • [Publications] 伊藤 克亘: "大語彙連続音声認識のための読み上げ文の選択" 日本音響学会研究発表講演論文集. 2-Q-7. (1997)

    • Related Report
      1996 Annual Research Report
  • [Publications] Alexandve Girardi: "Maximum likelihood successive state splitting algorithm for tied mixutre HMnet" 日本音響学会研究発表講演論文集. 3-6-1. (1997)

    • Related Report
      1996 Annual Research Report
  • [Publications] 北 研二: "音声言語処理-コーパスに基づくアプローチ" 森北出版, 169 (1996)

    • Related Report
      1996 Annual Research Report
  • [Publications] 小林 哲則: "音声データベース,人文学と情報処理" 勉誠社, 129 (1996)

    • Related Report
      1996 Annual Research Report

URL: 

Published: 1996-04-01   Modified: 2016-04-21  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi