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

1991 Fiscal Year Final Research Report Summary

Cooperative research on new speech recognition methods including hidden Markov models and neural networks

Research Project

Project/Area Number 01302032
Research Category

Grant-in-Aid for Co-operative Research (A)

Allocation TypeSingle-year Grants
Research Field 電子通信系統工学
Research InstitutionToyahashi University of Thechnology

Principal Investigator

NAKAGAWA Seiichi  Toyohashi University of Technology, Faculty of Engineering Professor, 工学部, 教授 (20115893)

Co-Investigator(Kenkyū-buntansha) UMESAKI Taizo  Chubu University, Faculty of Engineering Lecturer, 工学部, 講師 (40193932)
DANTSUJI Masatake  Kansai University, Faculty of Letters Associate Professor, 文学部, 助教授 (10188469)
KITAZAWA Shigeyoshi  Shizuoka University, Faculty of Engneering Associate Professor, 工学部, 助教授 (00109018)
KOBAYASHI Yutaka  Kyoto Institute of Technology, Faculty of Engineering and Design Assistant, 工芸学部, 助手 (40027917)
NIIMI Yasuhisa  Kyoto Institute of Technology, Faculty of Engineering and Design Professor, 工芸学部, 教授 (00026030)
Project Period (FY) 1989 – 1991
KeywordsMarkov model / HMM / neural network / speech recognition / language model
Research Abstract

Primary outcomes are in the following :
(a) in the field of hidden Markov model
Speaker adaptation of continuous HMM, combination of HMM and segmental statistics, consideration on semi-continuous HMM, new matrix-based calculation method for HMM, automatic construction of context-dependent HMM, learing of HMM by generalized descendent method,
(b) in the field of neural network
spoken word recognition by sequential neural network (neural Markov model), consideration on feed-forward neural network for pattern recognition (dimensionality reduction, estimation of probability density function). generalized sequential machine. theoretical analysis for approximation of continuous function by recurrent neural network
(c) in the field of acoustic/phonology and feature extraction
new acoustic feature model and feature hierarchies, extraction of distinctive feature by neural network, evaluation of smoothed group delay spectrum distance measure.
(d) in the field of language model
modeling of natural language by bigram/trigram/HMM/stochastic CFG, continuous stochastic CFG, analysis of phenomena in spoken dialog, sentence generation for QA system.
(e) in the field of continuous speech recognition system
context-free grammar driven time synchronous continuous speech recognition using HMM, segmented trellis HMM calculation algorithm for continuous speech recognition, LR - HMM based continuous speech recognizor

  • Research Products

    (50 results)

All Other

All Publications (50 results)

  • [Publications] 中川 聖一: "構文解析駆動型日本語連続音声認識システムーSPOJUSーSYNO" 電子情報通信学会論文誌. 72ーDーII. 1276-1283 (1989)

    • Description
      「研究成果報告書概要(和文)」より
  • [Publications] 中川 聖一: "連続音声認識・理解システムのための講文解析法の比較・検討" 情報処理学会論文誌. 30. 932-943 (1989)

    • Description
      「研究成果報告書概要(和文)」より
  • [Publications] Seiichi Nakagawa: "Speaker-independent continuos-speech recognition by phoneme based word spotring and time-synchronous Context-free pasing" Computer Speech and Language. 3. 277-299 (1989)

    • Description
      「研究成果報告書概要(和文)」より
  • [Publications] 中川 聖一: "連続音声認識システムの評価法ータスクの複雑性と文認識率との関係" 電子情報通信学会論文誌. 72ーDII. 683-693 (1990)

    • Description
      「研究成果報告書概要(和文)」より
  • [Publications] 中川 聖一: "連続出力分布型HMMによる日本語音韻認識" 日本音響学会誌. 46. 486-496 (1990)

    • Description
      「研究成果報告書概要(和文)」より
  • [Publications] 中川 聖一: "交通規則文に関する質問応答システムLICENCEにおける日本語文から一階述語論理式への変換" 情報処理学会論文誌. 32. 354-363 (1991)

    • Description
      「研究成果報告書概要(和文)」より
  • [Publications] 中川 聖一: "連続出力分布型HMMの話者適応による日本語音韻・音節認識" 日本音響学会誌. 47. 459-467 (1991)

    • Description
      「研究成果報告書概要(和文)」より
  • [Publications] Seiichi Nakagawa: "Comparison of syntaxーoriented spoken Japanese understanding system with semantic oriented system." 電子情報通信学会論文誌. E74. 1854-1862 (1991)

    • Description
      「研究成果報告書概要(和文)」より
  • [Publications] Seiich Nakagawa: "Comparison of language models by contextーfree grammar and quasi/simplifiedーtrigram" 電子情報通信学会論文誌. E74. 1897-1906 (1991)

    • Description
      「研究成果報告書概要(和文)」より
  • [Publications] 中川 聖一: "シ-ケンシャルニュ-ラルネットワ-クを用いた音声認識" 電子情報通信学会論文誌. 74ーDII. 1174-1183 (1991)

    • Description
      「研究成果報告書概要(和文)」より
  • [Publications] 中川 聖一: "固定長セグメントの統計量を用いたHMMによる音声認識" 電子情報通信学会論文誌. (1992)

    • Description
      「研究成果報告書概要(和文)」より
  • [Publications] Yutaka Kobayashi: "SUKITーIIーa speech understanding system based on robust phone spotting" 電子情報通信学会論文誌. E74. 1863-1869 (1991)

    • Description
      「研究成果報告書概要(和文)」より
  • [Publications] 壇辻 正剛: "音声デ-タベ-スのラベリングに関する一検討" 「日本語音声」研究報告. 3. 32-37 (1990)

    • Description
      「研究成果報告書概要(和文)」より
  • [Publications] 壇辻 正剛: "スペクトログラムを利用した音声デ-タベ-スの多層ラベリングに関する一検討" 「日本語音声」研究報告. 4. 46-47 (1990)

    • Description
      「研究成果報告書概要(和文)」より
  • [Publications] 板橋 秀一: "音声デ-タベ-スの作成・保存と利用に関する研究" 「日本語音声」研究報告. 6. (1992)

    • Description
      「研究成果報告書概要(和文)」より
  • [Publications] 梅崎 太造: "全極形フィルタの遅延スペクトルによる音声分析とその音声認識用スペクトル距離尺度への応用" 電子情報通信学会論文誌. J72ーDII. 1141-1150 (1989)

    • Description
      「研究成果報告書概要(和文)」より
  • [Publications] 梅崎 太造: "平滑化群遅延スペクトル距離尺度の特定話者音声認識における評価" 電子情報通信学会論文誌. J73ーA. 734-740 (1990)

    • Description
      「研究成果報告書概要(和文)」より
  • [Publications] 梅崎 太造: "平滑化群遅延スペクトル距離尺度の不特定話者音声認識における評価" 電子情報通信学会論文誌. J74ーA. 610-618 (1991)

    • Description
      「研究成果報告書概要(和文)」より
  • [Publications] Fikret S.Gurgen: "A study of line spectrum pair frequency repersentation for speech recognition" 電子情報通信学会論文誌. E75ーA. 98-102 (1992)

    • Description
      「研究成果報告書概要(和文)」より
  • [Publications] Yasuhisa Niimi: "A speech interface to an information netrieval system." Studia Phonologica. XXIV. 96-110 (1990)

    • Description
      「研究成果報告書概要(和文)」より
  • [Publications] Yasuo Ariki: "Effect of time duation and intrinsic features for English recognition" Studia Phonologica. XXIV. 70-82 (1990)

    • Description
      「研究成果報告書概要(和文)」より
  • [Publications] Shigeyoshi Kitazawa: "An artificial neural network for the burst point detection" Proc.of 1990 Int.Conf.on Spoken Language Processing. 1069-1072 (1990)

    • Description
      「研究成果報告書概要(和文)」より
  • [Publications] Naohiro Toda: "Polynomial Junctions can be realized by firite size multilayer feedforward neural networks" Proc.of IJCNN Singapore,. 343-348 (1991)

    • Description
      「研究成果報告書概要(和文)」より
  • [Publications] 中川 聖一,鹿野 清宏,東倉 洋一: "音声・聴覚と神経回路網モデル" オ-ム社, (1990)

    • Description
      「研究成果報告書概要(和文)」より
  • [Publications] 中川 聖一: "情報理論の基礎と応用" 近代科学社, (1992)

    • Description
      「研究成果報告書概要(和文)」より
  • [Publications] 壇辻 正剛: "シンバラ語の半鼻音(half nasals)に関する音響音韻学的研究「アジアの諸言語と一般言語学」" 三省堂, (1990)

    • Description
      「研究成果報告書概要(和文)」より
  • [Publications] 壇辻 正剛: "音声学と音韻論「講座日本語と日本語教育第11巻言語学要説(上)」" 明治書院, (1989)

    • Description
      「研究成果報告書概要(和文)」より
  • [Publications] Seiichi Nakagawa: "Syntax oriented spoken Japanese recognition/understanding system -SPOJUS-SYNO" Trans. IEICE. 72-D II-No. 8. 1276-1283 (1989)

    • Description
      「研究成果報告書概要(欧文)」より
  • [Publications] Seiichi Nakagawa: "Consideration on syntactic analysis for continuous speech recognition or understanding system" Trans, IPSJ. 30-No. 8. 932-943 (1989)

    • Description
      「研究成果報告書概要(欧文)」より
  • [Publications] Seiichi Nakagawa: "Speker-independent continuous-speech recognition by phoneme based word spotting and time-synchronous context-free parsing" Computer Speech Language. 3. 277-299 (1989)

    • Description
      「研究成果報告書概要(欧文)」より
  • [Publications] Seiichi Nakagawa: "An evaluation method for continuous speech recognition systems-Relationship between task complexity and sentence recognition accuracy-" Trans. IEICE. 72-D II-No. 5. 683-693 (1990)

    • Description
      「研究成果報告書概要(欧文)」より
  • [Publications] Seiichi Nakagawa: "Japanese phoneme recognition using continuous parameter hidden Markov models" Jour. ASJ. 46-No. 5. 486-496 (1990)

    • Description
      「研究成果報告書概要(欧文)」より
  • [Publications] Seiichi Nakagawa: "Translation from Japanese sentence to first order predicate calculus in question-answering system for traffic regulation LICENCE" Trans. IPSJ. 32-No. 3. 354-363 (1991)

    • Description
      「研究成果報告書概要(欧文)」より
  • [Publications] Seiichi Nakagawa: "Japanese phoneme/syllable recognition using speaker adaptation technique of continuous parameter HMM" Jour. ASJ. 47-No. 7. 23-32 (1991)

    • Description
      「研究成果報告書概要(欧文)」より
  • [Publications] Seiichi Nakagawa: "Comparison of syntax-oriented spoken Japanese understanding system with semantic oriented system" Trans. IEICE. E74-No. 7. 1854-1862 (1991)

    • Description
      「研究成果報告書概要(欧文)」より
  • [Publications] Seiichi Nakagawa: "Comparison of language models by context-free grammar an quasi/simplified-trigram" Trans. IEICE. E74-No. 7. 1897-1906 (1991)

    • Description
      「研究成果報告書概要(欧文)」より
  • [Publications] Seiichi Nakagawa: "Speech recognition using various sequential networks" Trnas. IEICE. 74D-II-No. 9. 1174-1183 (1991)

    • Description
      「研究成果報告書概要(欧文)」より
  • [Publications] Seiichi Nakagawa: "Syllable recognition by hidden Markov model using fixed-length segmental statistics" Trnas. IEICE. 75-DII. (1992)

    • Description
      「研究成果報告書概要(欧文)」より
  • [Publications] Yutaka Kobayashi: "SUSKIT-II-a speech understanding system based on robust phone spotting" Trans. IEICE. E74-No. 7. 1863-1869 (1991)

    • Description
      「研究成果報告書概要(欧文)」より
  • [Publications] Masatake Dantsuji: "A study on labeling of speech database Japanese Speech" Japanese Speech. 3. 32-37 (1990)

    • Description
      「研究成果報告書概要(欧文)」より
  • [Publications] Masatake Dantsuji: "A study on multi-layer labeling of speech database using sound spectrogram" Japanese Speech. 4. 46-47 (1990)

    • Description
      「研究成果報告書概要(欧文)」より
  • [Publications] Shiuichi Itahashi: "A study on making, preservation, and utilization of database" Japanese Speech. 6. (1992)

    • Description
      「研究成果報告書概要(欧文)」より
  • [Publications] Taizo Umezaki: "Speech analysis by group delay spectrum of all-pole filters and its application to the spectrum distance measure for speech recognition" Trans. IEICE. J72-D II, No. 8. 1141-1150 (1989)

    • Description
      「研究成果報告書概要(欧文)」より
  • [Publications] Taizo Umezaki: "Evaluation of the smoothed group delay spectrum distance measure for speaker-dependent speech recognition" Trans. IEICE. J73-A, No. 4. 734-740 (1990)

    • Description
      「研究成果報告書概要(欧文)」より
  • [Publications] Taizo Umezaki: "Evaluation of the smoothed group delay distance measure for speaker-independent speech recognition." Trans. IEICE. J74-A, No. 4. 610-618 (1991)

    • Description
      「研究成果報告書概要(欧文)」より
  • [Publications] Fikret S. Gurgen: "A study of line spectrum pair frequency representation of speech recognition." Trans. IEICE. E75-A, No. 1. 98-102 (1992)

    • Description
      「研究成果報告書概要(欧文)」より
  • [Publications] Yasuhisa Niimi: "A speech interface to an information retrieval system." Studia Phonologica. XXIV. 96-110 (1990)

    • Description
      「研究成果報告書概要(欧文)」より
  • [Publications] Yasuo Ariki: "Effect of time duration and intrinsic features for English recognition." Studia Phonologica. XXIV. 70-82 (1990)

    • Description
      「研究成果報告書概要(欧文)」より
  • [Publications] Shigeyoshi Kitazawa: "An artificial neural network for the burst point detection" Proc. of 1990 Int. Conf. on Spoken Language Processing. 1069-1072 (1990)

    • Description
      「研究成果報告書概要(欧文)」より
  • [Publications] Naohiro Toda: "Polynomial juncion can be realized by finite size multilayer feedforward neural networks" Proc. of IJCNN Singapore. 343-348 (1991)

    • Description
      「研究成果報告書概要(欧文)」より

URL: 

Published: 1993-03-16  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi