学術論文 (Full Papers)

(発表時期逆順。1999年11月現在)
  1. 嵯峨山 茂樹, 板倉 文忠: ``線形予測符号化と複合正弦波モデル化の対称性,'' 電子情報通信学会論文誌 A, 投稿中.
  2. 高橋 敏, 嵯峨山 茂樹: ``学習移動ベクトルの相関関係を用いた音響モデルの 話者適応化,'' 電子情報通信学会論文誌 D-II, Vol. J82-D-II, No. 3, pp. 324--331, 1999.
  3. 高橋 敏, 嵯峨山 茂樹: ``4階層共有構造の音響モデルによる音声認識,'' 電子情報通信学会論文誌 D-II, Vol. J82-D-II, No. 3, pp. 315--323, 1999.
  4. Mikio Kitai, Kazuo Hakoda, and Shigeki Sagayama, ``ASR and TTS Telecommunications Applications in Japan,'' Speech Communication, Vol. 23, No. 1-2, pp. 17-30, Oct. 1997.
  5. Jun-ichi Takahashi and Shigeki Sagayama, ``Vector-Field-Smoothed Bayesian Learning for Fast and Incremental Speaker/Telephone-Channel Adaptation,'' Computer Speech and Language, Vol. 11, No. 2, pp. 127--146, Apr. 1997.
  6. 吉岡理, 荒井和博, 管村昇, 嵯峨山茂樹, ``音声認識機能を含むマルチモ−ダ ルインタフェ−スを持つ住所入力システムの開発と評価,'' 電子情報通信学会 論文誌D2分冊, Vol. J80-D-II, No. 5, pp. 1007--1015, May 1997.
    Osamu Yoshioka, Kazuhiro Arai, Noboru Sugamura, Shigeki Sagayama, ``An Address Data Entry System Utilizing Multi-Modal Interface Employing Speech Recognition,'' Trans. IEICE, Vol. J80-D-II, No. 5, pp. 1007--1015, May 1997.
  7. Jun-ichi Takahashi and Shigeki Sagayama, ``Discriminative Training Based on Minimum Classification Error for a Small Amount of Data Enhanced by Vector-Field-Smoothed Learning,'' IEICE Trans., Vol. E79-D, No. 12, Dec 1996.
  8. Tetsuo Kosaka, Shoichi Matsunaga, and Shigeki Sagayama, ``Speaker-independent Speech Recognition Based on Tree-Structured Speaker Clustering,'' Computer Speech and Language, Vol. 10, pp. 55--74, 1996.
  9. 野田 喜昭, 嵯峨山 茂樹, ``前向きヒューリスティック関数を用いたビーム探 索によるHMM-LR連続音声認識,'' 電子情報通信学会論文誌 D-II, Vol. J79-D-II, No. 8, pp. 1326--1334, 1996.
    Yoshiaki Noda, Shigeki Sagayama, ``Beam Search Using Forward Heuristic Functions for HMM-LR Continuous Speech Recognition,''IEICE Trans. Vol. J79-D-II, No. 8, pp. 1326--1334, 1996.
  10. 村上 仁一, 嵯峨山 茂樹, ``自由発話音声における音響的な特徴の検討,'' 電子情報通信学会論文誌 D-II, Vol. J78-D-II, No.12, pp. 1741-1749, Dec 1995.
    Jin-ichi Murakami, and Shigeki Sagayama, ``A Discussion of Acoustic Problems in Spontaneous Speech Recognition,'' Trans. IEICE D-II, Vol. J78-D-II, No.12, pp. 1741-1749, Dec 1995.
  11. Jun-ichi Takahashi, Noboru Sugamura, Tomohisa Hirokawa, Shigeki Sagayama, and Sadaoki Furui, ``Interactive Voice Technology Developement for Telecommunications Applications,'' Speech Communication, Vol. 17, No. 3-4, pp. 287--301, 1995.
  12. Yasunaga Miyazawa, Jun-ichi Takami, Shigeki Sagayama, and Shoichi Matsunaga, ``All-phoneme Ergodic Hidden Markov Network for Unsupervised Speaker Adaptation Method,'' IEICE Transactions on Info. \& Syst., Vol. E78-D, No. 8, pp. 1044--1050, Aug. 1995.
  13. Kouichi Yamaguchi, Harald Singer, Shoichi Matsunaga, Shigeki Sagayama, ``Speaker-consistent Parsing for Speaker-independent Continuous Speech Recognition,'' Trans. IEICE Inf. \& Syst., Vol. E78-D, No. 6, pp. 719-724, Jun. 1995.
  14. Tetsuo Kosaka, Shigeki Sagayama, ``Automatic Determination of the Number of Mixture Components for Continuous HMMs Based on a Uniform Variance Criterion,'' Trans. IEICE Inf. \& Syst., Vol. E78-D, pp. 642--647, No.6, June 1995.
  15. Ryosuke Isotani, Shoichi Matsunaga, Shigeki Sagayama, ``Speech Recognition Using Function-Word $N$-grams and Content-Word $N$-grams,'' Trans. IEICE Inf. \& Syst., Vol. E78-D, No. 6, pp. 692--697, June 1995.
  16. 小坂 哲夫, 松永 昭一, 嵯峨山 茂樹, ``木構造話者クラスタリングを用いた 話者適応,'' 電子情報通信学会論文誌, Vol. J78-D-II, No. 1, pp. 1--9, Jan 1995.
    (1996年 電子情報通信学会論文賞)
  17. 鷹見 淳一, 嵯峨山 茂樹, ``隠れマルコフ網で表現した音素コンテキスト依存 モデルのための話者適応,'' 電子情報通信学会論文誌 D-II, Vol. J77-D-II, No. 12, pp. 2325--2333, Dec 1994.
    Jun-ichi Takami, Shigeki Sagayama, ``A Speaker Adaptation Technique for Context Dependent Models Represented by Hidden Markov Networks,'' Trans. IEICE, D-II, Vol. J77-D-II, No. 12, pp. 2325--2333, Dec 1994.
  18. 永井 明人, 鷹見 淳一, 嵯峨山 茂樹, ハラルド シンガー, ``隠れマルコフ網 と一般化 LR 構文解析を統合した連続音声認識,'' 電子情報通信学会論文誌 D-II, Vol. J77-D-II, No. 1, pp. 9--19, Jan 1994.
    Akito Nagai, Jun-ichi Takami, Shigeki Sagayama, Harald Singer, ``Continuous Speech Recognitoi Integrating Hidden Markov Networks and a Generalized LR Parser,'' Trans. IEICE D-II, Vol. J77-D-II, No. 1, pp. 9--19, Jan 1994.
  19. Masatake Dantsuji, Shigeki Sagayama, and Shuji Doshita, ``A study on Distinctive Features and Feature Hierarchies through Phoneme Environment Clustering (PEC),'' Bulletin of University of Kyoto, pp. --, 1994.
  20. Harald Singer and Shigeki Sagayama, ``Pitch Dependent Phone Modelling for HMM Based Speech Recognition,'' Journal of ASJ(E), Vol. 15, No. 2, pp. 77--86, 1994.
  21. Kenji Kita, Tsuyoshi Morimoto, Kazumi Ohkura, Shigeki Sagayama, Yoneo Yano, ``Spoken Sentence Recognition Based on HMM-LR with Hybrid Language Medeling,'' Trans. IEICE Inf. \& Syst., Vol. E77-D, No. 2, pp. 258--265, Feb 1994.
  22. 永井 明人, 北 研二, 花沢 利行, 川端 豪, 鹿野清宏, 森元 逞, 嵯峨山 茂樹, 榑松 明, 鈴木 忠, 岩崎 知弘, 中島 邦男, ``HMM と一般化 LR 構文解析を用 いた実時間大語彙連続音声認識装置の実現,'' 日本音響学会誌, Vol. 50, No. 9, pp. 723--729, 1994.
    Akito Nagai, Kenji Kita, Toshiyuki Hanazawa, Takeshi Kawabata, Kiyohiro Shikano, Tsuyoshi Morimoto, Shgeki Sagayama, and Akira Kurematsu, ``Realization of Realtime Large Vocabulary Continuous Speech Recognition Integrating Hidden Markov Models and Generalized LR Parser,'' Jour. Acoust. Soc. Japan, Vol. 50, No. 9, pp. 723--729, 1994.
  23. 中井 満、下平 博、嵯峨山 茂樹, ``ピッチパターンのクラスタリングに基づ く不特定話者連続音声の句境界検出,'' 電子情報通信学会論文集 A, Vol. J77-A, No. 2, pp. 206--214, Feb 1993.
    Mitsuru Nakai, Hiroshi Shimodaira, Shigeki Sagayama, ``Prosodic Phrase Segmentation Based on Pitch-Pattern Clustering,'' Trans. IEICE A, Vol. J77-A, No. 2, pp. 206--214 (Feb 1993).
  24. 宮沢 康永, 大倉 計美, 嵯峨山 茂樹 , ``全音素エルゴディック HMM を用い た教師なし話者適応,'' 電子情報通信学会論文誌A, Vol. J77-A, No. 2, pp. 112--119, Feb 1994.
    Yasunaga Miyazawa, Kazumi Ohkura, Shigeki Sagayama, ``Unsupervized Speaker Adaptation Using All-Phoneme Ergodic HMM,'' Trans. IEICE, Vol. J77-A, No. 2, pp. 112--119, Feb 1994.
  25. 小坂 哲夫, 鷹見 淳一, 嵯峨山 茂樹, ``話者混合逐次状態分割法による不特 定話者音声認識と話者適応,'' 電子情報通信学会論文誌A, Vol. J77-A, No. 2, pp. 103--111, Feb 1994.
    Tetsuo Kosaka, Jun-ichi Takami, Shigeki Sagayama, ``Speaker-Independent Speech Recognition and Speaker adaptation Using Speaker-Mixture Successive State Splitting Algorithm,'' IEICE Trans, A, Vol. J77-A, No. 2, pp. 103--111 (Feb 1994).
  26. 鷹見 淳一, 嵯峨山 茂樹, ``逐次状態分割法による隠れマルコフ網の自動生成,'' 電子情報通信学会論文誌 D-II, Vol. J76-D-II, No. 10, pp. 2155--2164, Oct 1993.
    Jun-ichi Takami, Shigeki Sagayama, ``Automatic Generation of Hidden Markov Networks by a Successive State Splitting Algorithm,'' Trans. IEICE, Vol. J76-D-II, No. 10, pp. 2155--2164, Oct 1993.
  27. Kazuki Katagishi, Kiyoaki Aikawa, Harald Singer and Shigeki Sagayama, ``Feature Extraction Using a Matrix Coefficient Filter for Speech Recognition,'' Speech Communication, Vol. 13, pp. 297--306, North-Holland, 1993.
  28. Harald Singer and Shigeki Sagayama, ``Suprasegmental Duration Control with Matrix Parsing in Continuous Speech Recognition,'' Speech Communication, Vol. 13, pp. 315--322, North-Holland, 1993.
  29. 大倉 計美, 杉山 雅英, 嵯峨山 茂樹, ``混合連続分布HMM移動ベクトル場平滑 化話者適応方式,'' 電子情報通信学会論文誌 D-II, Vol. J76-D-II, No. 12, pp. 2469--2476, Dec 1993.
    Kazumi Ohkura, Masahide Sugiyama, Shigeki Sagayama, ``Speaker Adaptation Based on Transfer Vector Field Smoothing Method with Continuous Mixture Density HMMs,'' IEICEJ Trans D-II, Vol. J76-D-II, No. 12, pp. 2469--2476, Dec 1993.
  30. Hiroaki Hattori, Satoshi Nakamura, Kiyohiro Shikano and Shigeki Sagayama, ``Speaker Weighted Training of HMM Using Multiple Reference Speakers,'' Trans. IEICE Inf. \& Syst., Vol.E76-D, No. 2, Feb 1993.
  31. Hiroaki Hattori and Shigeki Sagayama, ``Speaker Adaptation Based on Vector Field Smoothing,'' IEICE Trans Inf. \& Syst., Vol. E76-D, No. 2., Feb 1993.
  32. Akito Nagai, Shigeki Sagayama, Kenji Kita, and Hideaki Kikuchi, ``Three Different LR Parsing Algorithms for Phoneme-Context-Dependent HMM-Based Continuous Speech Recognition,'' IEICE Trans Inf. \& Syst., Vol. E76-D, No. 1, pp. 29--37, Jan 1993.
  33. Kenji Kita, Tsuyoshi Morimoto, and Shigeki Sagayama, ``LR Parsing with a Category Reachability Test Applied to Speech Recognition,'' IEICE Trans Inf. \& Syst., Vol. E76-D, No. 1, pp. 23--28, Jan 1993.
  34. David Rainton and Shigeki Sagayama, ``Minimum Error Classification Training of HMMs --- Implementation Details and Experimental Results ---,'' J. Acoust. Soc. Japan (E), Vol. 13, No. 6, pp. 379--387, Oct 1992.
  35. Jun-ichi Takami, Atsuhiko Kai, and Shigeki Sagayama, ``A Pairwise Discriminant Approach Using Artificial Neural Networks for Continuous Speech Recognition,'' The Journal of the Acoustical Society of Japan, Vol. 13, No. 6, pp. 411-418, Nov 1992.
  36. 小森 康弘, A. H. Waibel, 嵯峨山 茂樹, ``ニューラル・ファジー学習法によ る音声認識の性能向上,'' 電子情報通信学会論文誌 D-II, Vol. J75-D-II, No. 7, pp. 1101-1110, 1992.
    Yasuhiro Komori, Alexander H. Waibel, Shigeki Sagayama, ``A Neural Fuzzy Training Approach for Improving Speech Recognition,'' Trans. IEICE, D-II, Vol. J75-D-II, No. 7, pp. 1101-1110, 1992.
  37. Fikret S. Gurgen, Shigeki Sagayama, and Sadaoki Furui, ``A Study of Line Spectrum Pair Frequency Representation for Speech Recognition,'' Trans. IEICE Fundamentals, Vol. E75-A, No. 1, pp. 98--102, Jan 1992.
  38. Satoshi Takahashi, Shoichi Matsunaga, and Shigeki Sagayama, ``Isolated Words Recognition Using Pitch Pattern Information,'' Trans. IEICE Fundamentals, Vol. E76-A, No. 2, Feb 1993.
  39. 嵯峨山 茂樹, 板倉 文忠, ``複合正弦波モデルによる音声スペクトルの分析,'' 電子通信学会論文誌, Vol. J64-A, No. 2, pp. 105--112, Feb 1981.
    Shigeki Sagayama, Fumitada Itakura, ``Composite Sinusoidal Modeling Applied to Spectral Analysis of Speech,'' Trans. IEICE, Vol. J64-A, No.2, pp. 105--112, Feb 1981.
  40. 藤村 貞夫, 嵯峨山 茂樹, ``図形の分離と特徴抽出,'' 計測自動制御学会論文 集, Vol. 10, No. 1, pp. 127--133, 1974.
    Sadao Fujimura, Shigeki Sagayama, ``Segmentation and Feature Extraction of Patterns,'' Trans. of SICE, Vol. 10, No. 1, pp. 127--133, 1974.