Kawabata's Recent Papers

［論文］

  1. 今西 諒, 川端 豪：「混合ガウスモデル話者認識における繰り返し推定回数の検討」, 音学誌, 78, 11, pp.650-653 (Nov. 2022)

    2. #Imanishi, R., Kawabata, T.: "A study to determine the number of Expectation-Maximization iterations for Gaussian-Mixture-Model based speaker recognition," J. Acoust. Soc. Jpn., 78, 11, pp.650-653 (Nov. 2022)

  2. 高見 純子, 川端 豪：「混合ガウスモデル適応速度と到達精度に基づく少人数音声対話システムへの利用を想定した話者認識性能尺度」, 音学誌, 76, 5, pp.254-261 (May 2020)

    3. #Takami, J. and Kawabata, T.: "Speaker recognition performance measure based on adaptation quickness and final accuracy for spoken dialog systems," J. Acoust. Soc. Jpn., 76, 5, pp.254-261 (May 2020)

  3. Kawabata, T., Fujiwara, M. and Shibutani, T.: "Detection of Speaker Direction based on the On-and-Off Microphone Combination for Entertainment Robots," Entertainment Computing - ICEC2005, Lecture Notes in Computer Science, Springer, LNCS-3711, pp.248-255 (Sep. 2005)


  4. 川端 豪： 「二項事後分布に基づく N-gram 記号連鎖確率の推定」, 音学誌, 61, 8, pp.441-447 (Aug. 2005)

    5. #Kawabata, T.: "Estimation of N-gram probabilities based on the Binomial Posteriori Distribution," J. Acoust. Soc. Jpn., 61, 8, pp.441-447 (Aug. 2005)

  5. 杉山 聡, 堂坂 浩二, 川端 豪: 「音声対話によるテキスト内容の伝達方法」 情報処理学会論文誌, 41, 6, pp.1883-1894 (平成１２年)

    6. #Sugiyama, A., Dohsaka, K. and Kawabata, T.: "A Method for Conveying the Contents of Written Texts by Spoken Dialogue," IPSJ Trans., 41, 6, pp.1883-1894 (2000)

  6. 川端豪: 「確率文法と 話題マルコフモデルに基づく 音声認識のための 話題制御」, 信学論ＤＩＩ, J77-DII, 10, pp.1967-1972 （平成６年１０月）

    7. #Kawabata, T. : "Topic Focusing Mechanism for Speech Recognition based on Probabilistic Grammar and Topic Markov Model," IEICE Trans., J77-DII,10, pp.1967-1972 (Oct. 1994)

  7. 永井明人, 北研二, 花沢利行, 川端豪, 鹿野清宏, 森本逞, 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」, 音学誌, 50, 9, pp.723-729 （平成６年９月）

    8. #Nagai, A., Kita, K., Hanazawa, T., Kawabata, T., Shikano, K., Morimoto, T., Sagayama, S., Kurematsu, A., Suzuki, T., Iwasaki, T., Nakazima, K. : "Realization of Real-time Large Vocabulary Continuous Speech Recognition Integrating Hidden Markov Models and Generalized LR Parser," J. Acoust. Soc. Jpn., 50, 9, pp.723-729 (Sep. 1994)

  8. 山田智一, 松永昭一, 川端豪, 鹿野清宏: 「音声認識における 仮名・漢字 文字連鎖確率に 基づく 統計的言語モデルの 利用」, 信学論Ａ, J77-A, 2, pp.198-205 （平成６年２月）

    9. #Yamada, T., Matsunaga, S., Kawabata, T. and Shikano, K. : "Speech Recognition Using Stochastic Language Models Based on a Priori Probabilities of Kana and Kanji Characters," IEICE Trans., J77-A, 2, pp.198-205 (Feb. 1994)

  9. Shikano, K., Yamada, T., Kawabata, T., Matsunaga, S. and Hanazawa, T. : "Dictation Machine Based on Japanese Character Source Modeling," International Journal of Pattern Recognition and Artificial Intelligence, 8, 1, pp.181-196 (1994)


  10. 川端豪: 「不特定話者 音声認識のための 予測子コードブックの 構成法」, 信学論ＤＩＩ, J75-DII, 11, pp.1770-1777 （平成４年１１月）

    11. #Kawabata, T. : "Predictor Codebooks for Speaker-Independent Speech Recognition," IEICE Trans., J75-DII, 11, pp.1770-1777 (Nov. 1992)

  11. Kawabata, T. : "Generalization Effects of k-Neighbor Interpolation Training, " Neural Computation, 3, pp.409-417 (1991)


  12. Kawabata, T., Hanazawa, T., Itoh, K. and Shikano, K. : "Japanese Phonetic Typewriter Using HMM Phone Recognition and Stochastic Phone-Sequence Modeling," IEICE Trans., E74, 7, pp.1783-1787 (July 1991)


  13. Kita, K., Kawabata, T. and Hanazawa, T. : "HMM Speech Recognition Using Stochastic Language Models," J. Acoust. Soc. Jpn. (E), 12, 3, pp.99-105 (1991)


  14. 北研二, 川端豪, 斉藤博昭: 「ＨＭＭ音韻認識と 拡張ＬＲ構文解析法を 用いた 連続音声認識」, 情処論, 31, 3, pp.472-480 （平成２年３月）

    15. #Kita, K., Kawabata, T. and Saito, H. : "HMM Continuous Speech Recognition Using Generalized LR Parsing," Info. Proc. Soc. Jpn. Trans., 31, 3, pp.472-480 (Mar. 1990)

［国際会議］

  1. Kawabata, T.: "Object-Oriented Dialog Management Architecture for Designing Multi-Purpose Spoken Dialog Systems," The 18th International Congress on Acoustics (ICA-2004) (Apr. 2004)


  2. Nakano, M., Dohsaka, K., Miyazaki, N., Hirasawa, J., Tamoto, M., Kawamori, A., Sugiyama, A., and Kawabata T. : "Handling Rich Turn-Taking in Spoken Dialogue Systems,"European Conference on Speech Communication and Technology (EUROSPEECH-99), 3, pp.1167-1170 (1999)


  3. Nakano, M., Miyazaki, N., Hirasawa, J., Dohsaka, K., and Kawabata, T. : "Understanding Unsegmented User Utterances in Real-Time Spoken Dialogue Systems," Annual Meeting of the Association for Computational Linguistics (ACL-99) (1999)


  4. Sugiyama, A., Dohsaka, K., and Kawabata, T. : "A Method for Conveying the Contents of Written Texts by Spoken Dialogue," Proceedings of Pacific Association for Computational Linguistics (PACLING '99) (1999)


  5. Kawabata, T. : "Emergent Computational Dialogue Management Architecture for Task-Oriented Spoken Dialogue Systems," ICSLP-98, 4, 1215-1218 (Nov. 1998)


  6. Hirasawa, J., Miyazaki, N., Nakano, M., and Kawabata, T. : "Implementation of Coordinative Nodding Behevior on Spoken Dialogue System," ICSLP-98, 6, pp.2347-2350 (Nov. 1998)


  7. Kawabata, T. and Tamoto, M. : "Back-off Method for N-gram Smoothing based on Binomial Posteriori Distribution," ICASSP-96, I, pp.192-195 (May 1996)


  8. Kawabata, T. : "Topic Focusing Mechanism for Speech Recognition based on Probabilistic Grammar and Topic Markov Model," ICASSP-95, I, pp.317-320 (May 1995)


  9. Tamoto, M. and Kawabata, T. : "Clustering Word Category based on Binomial Posteriori Cooccurence Distribution," ICASSP-95, TP7-, pp. (May 1995)


  10. Kawabata, T. : "Dynamic Probabilistic Grammar for Spoken Language Disambiguation," ICSLP-94, S16-3.1, pp.787-790 (Sep. 1994)


  11. Nakatani, T., Kawabata, T. and Okuno, H. G. : "Unified Architecture for Auditory Scene Analysis and Spoken Language Processing," ICSLP-94, S24-3.1, pp.1403-1406 (Sep. 1994)

［研究会］

  1. Imanishi, R., Kawabata, T.: "Short-duration Speaker Recognition Based on Gaussian Mixture Model and Missing Feature Theory," IPSJ SIG Technical Reports, Vol.2022-SLP-144, No.7, pp.1-5 (Nov. 2022)

    2. #今西 諒, 川端 豪：「混合ガウスモデルと特徴欠損理論に基づく短時間発話からの話者認識」, 情処研報, Vol.2022-SLP-144, No.7, pp.1-5 (Nov. 2022)

  2. 込山 航大, 川端 豪：「二項事後分布に基づくN-gram言語モデルにおける継承係数の文脈依存性の検討」, 情処研報, Vol.2022-SLP-144, No.9, pp.1-4 (Nov. 2022)

  3. 野田 脩介, 川端 豪：「GMM適応に基づく話者認識における混合要素整合の検討」, 情処研報, Vol.2021-SLP-139, No.5, pp.1-6 (Dec. 2021)

    4. #Noda, S. and Kawabata, T.: "A Study of Mean Order Alignments for the GMM Adaptation-based Speaker Recognition," IPSJ SIG Technical Reports, Vol.2021-SLP-139, No.5, pp.1-6 (Dec. 2021)

  4. 高見 純子, 川端 豪：「GMM適応速度と到達精度に基づく音声対話システムフロントエンドのための話者認識性能の評価法」, 信学技報, Vol.118, No.426, SP2018-59, pp.35-40 (Jan. 2019)

    5. #Takami, J. and Kawabata, T.: "Speaker recognition performance measure based on adaptation quickness and final accuracy for spoken dialog systems," Journal of Acoustical Society of Japan, Vol.78, No.5, pp.254-261 (May 2020)

  5. 木下 悠，川端 豪： 「車載情報機器の音声操作におけるタイムアウト制御の実験的評価」, 情処研報, Vol.2015-SLP-108, No.1, pp.1-5 (Oct. 2015)

    6. #Kinoshita, Y. and Kawabata, T.: "Evaluation of Timeout Control Methods for Voice Command Telematics Systems," IPSJ SIG Technical Reports, Vol.2015-SLP-108, No.1, pp.1-5 (Oct. 2015)

  6. 木下 悠，川端 豪： 「車載情報機器の音声操作における文脈の保持とタイムアウト制御」, 情処研報, Vol.2014-SLP-104, No.18, pp.1-6 (Dec. 2014)

    7. #Kinoshita, Y. and Kawabata, T.: "Timeout Controls of the Voice Command Context for Telematics Systems," IPSJ SIG Technical Reports, Vol.2014-SLP-104, No.18, pp.1-6 (Dec. 2014)

  7. 藤原真志, 川端 豪:「近接-遠隔マイクコンビネーションによる全方位型話者方向同定」, 信学技法, Vol.106, No.122, SP2006-8, pp.13-18 (June 2006)

    8. #Fujiwara, M. and Kawabata, T."All-directional Speaker Localization Mechanism based on the On-and-Off Microphone Combination," Tech. Rep. IEICE, SP2006-8, pp.13-18 (June 2006)

  8. 渋谷貴紀, 川端 豪:「音声対話システムのための親近感特徴量の探索」, 信学技法, Vol.106, No.122, SP2006-10, pp.25-30 (June 2006)

    9. #Shibutani, T. and Kawabata, T."Extraction of Prosodic Intimacy Features for Spoken Dialog Systems," Tech. Rep. IEICE, SP2006-8, pp.13-18 (June 2006)

  9. 清信将範, 川端 豪:「ドライビングシミュレータの走行精度による車載情報機器の負荷 測定」, 信学技法, Vol.106, No.123, SP2006-13, pp.13-18 (June 2006)

    10. #Kiyonobu, M. and Kawabata, T."An Approach of Workload Measurement based on Simulation Driving Accuracy," Tech. Rep. IEICE, SP2006-8, pp.13-18 (June 2006)

  10. 川端豪：「BPD Back-off 法における継承係数の決定法」, 信学技法, SP96-63, pp.19-24 (平成８年１１月)

    11. #Kawabata, T. : "How to Determine the Inheritance Factors of BPD Back-off N-gram Smoothing Method," Tech. Rep. IEICE, SP96-63, pp.19-24 (Nov. 1996)

  11. 川端豪, 田本真詞：「二項事後分布に基づく n-gram 言語モデルの back-off 平滑化」, 信学技報, SP95-93, pp.1-6 (平成７年１２月)

    12. #Kawabata, T. and Tamoto, M.: "Back-off Method for N-gram Smoothing based on Binomial Posteriori Distribution", Tech. Rep. IEICE, SP95-93, pp.1-6 (Dec. 1995)

  12. 田本真詞, 川端豪: 「連接共起に 注目した 単語の クラスタリング」, 信学技報, SP93-125, pp.55-62 （平成６年１月）

    13. #Tamoto, M. and Kawabata, T. : "Aspects of Clustering based on Bigram Occurrency," Tech. Rep. IEICE, SP93-125, pp.55-62 (Jan. 1994)

  13. 川端豪: 「確率文法と 話題マルコフモデルに 基づく 音声認識のための 話題制御」, 信学技報, SP93-115, pp.7-13 （平成５年１２月）

    14. #Kawabata, T. : "Topic Focusing Mechanism for Speech Recognition, based on Probabilistic Grammar and Topic Markov Model," Tech. Rep. IEICE, SP93-115, pp.7-13 (Dec. 1993)

［全国大会］

  1. 高見 純子, 川端 豪：「GMMスーパーベクトルに基づく話者認識における特徴空間の構成法」, 音講論集(2018秋), 2-Q-14, pp.1075-1076 (Sep. 2018)

    2. #Takami, J. and Kawabata, T.: "A study of GMM supervector spaces for speaker recognition," Proc. ASJ 2018 Autumn Meeting, 2-Q-14, pp.1075-1076 (Sep. 2018)

  2. 田本真詞, 川端豪: 「連接共起に 注目した 単語の クラスタリング」, 音講論集, 1-Q-22, pp.153-154 （平成６年３月）

    3. #Tamoto, M. and Kawabata, T. : "Aspects of Clustering based on Bigram Occurrency," Proc. ASJ meeting, 1-Q-22, pp.153-154 (Mar. 1994)

  3. 川端豪: 「音声理解システム JUNO における 話題制御」, 音講論集, 1-8-14, pp.27-28 （平成５年１０月）

    4. #Kawabata, T. : "Topic Focusing Mechanism of Speech Understanding System JUNO," Proc. ASJ meeting, 1-8-14, pp.27-28 (Oct. 1993)

Last update: Nov. 30, 2022 by T. Kawabata