西村雅史 (NISHIMURA Masafumi)

 

Profile

2014年4月末でIBM東京基礎研究所を退職し,静岡大学大学院情報学研究科に着任しました。
IBMではほぼ30年間,一貫して大語彙連続音声認識に関する研究を行なってきましたが, 現在はその研究経験を生かし,音声認識だけでなく,医用情報処理や高齢者・障害者支援のための応用研究にも取り組んでいます。 「音を中心としたセンサー情報処理技術や深層ニューラルネットなどの自動認識技術を駆使して”人間の機能を補助・拡張すること”」が現在の私の研究テーマです。

こちらもご覧ください。特に音情報処理技術の医療応用について話しています。>> 静岡大学テレビジョン 研究者紹介(西村雅史) 2020.2.3公開


*** 現在取り組んでいる主な研究課題 ***
・医用情報処理(摂食嚥下の自動評価,音声による認知症スクリーニング,ALS患者の咳嗽モニタリング)
・高齢者支援(回想法音声対話システム,心身状態の認識・見守りシステム)
・障害者支援(聴覚障害者用音声認識,聴覚障害児学習支援,母子コミュニケーション分析)
・音声認識の高精度・高機能化(高騒音下多人数会話音声認識)


略 歴

  • 1981年3月 大阪大学基礎工学部生物工学科卒業
  • 1983年3月 大阪大学大学院基礎工学研究科物理系修了
  • 1983年4月 日本IBM Japan Science Institute(後のIBM東京基礎研究所)入社
    以来,基礎研究所にてViaVoiceなど主に大語彙音声認識ソフトウェアの研究開発に従事
  • 2003年1月 IBM Senior Technical Staff Member(主席研究員)
  • 2014年4月 日本IBM退職
  • 2014年5月 静岡大学大学院情報学研究科(教授)
  • 2015年4月 静岡大学大学院総合科学技術研究科情報学専攻(教授)
    (兼担)静岡大学創造科学技術大学院インフォマティクス部門(教授)
  • 2017年4月 国立研究開発法人産業技術総合研究所客員研究員
  • 2017年4月 静岡大学情報学部キャリア支援室長(2019.3まで)
  • 2018年4月 情報処理学会音声言語情報処理研究会(SLP)主査
  • 2019年4月 静岡大学情報学部情報学研究推進室長
  • 2019年4月 日本音響学会東海支部支部長
  • 2019年7月 文科省科学技術専門家ネットワーク専門調査員

  • 学 位

  • 博士(工学)

  • 所属学会

  • IEEE (Senior Member)
  • 電子情報通信学会(シニア会員)
  • 情報処理学会(シニア会員, 代表会員,SLP研究会主査)
  • 日本音響学会(東海支部支部長)
  • 人工知能学会
  • 信号処理学会
  • ISCA
  • APSIPA

  • 担当講義

  • 情報学総論
  • 情報学方法論
  • 人工知能
  • プログラミング
  • 先端情報学実習
  • 情報資源総論 (大学院,英語講義)
  • 音声情報処理論 (大学院,英語講義)
  • インフォマティクス論 (創造科学技術大学院,英語講義)
  • 新入生セミナー

  • Masafumi Nishimura received his B.E. and M.E. degrees in Biophysical Engineering from Osaka University in 1981 and 1983, and his Dr. of Engineering degree from Toyohashi University of Technology in 1998. In 1983 he joined the IBM Japan Science Institute and worked in speech recognition area. Since 2003, he had been a Senior Technical Staff Member of IBM and a Manager of the Speech Technology Group at the IBM Research - Tokyo, Japan. In 2014, he moved to the Shizuoka University as a Professor of Informatics. His research interests include speech signal processing, robust speech recognition, statistical language modeling, expressive speech synthesis, emotion detection and speech analytics. Dr. Nishimura became Editor of the Institute of Electronics, Information and Communication Engineers Transactions in 2010. He received the SIG Research Award from the Information Processing Society of Japan in 1998, and the Prize for Outstanding Technological Development in Acoustics from the Acoustical Society of Japan in 1999. He is a Senior Member of the IEEE, the IEICE and the IPSJ, and a Member of the ASJ and the JSAI.

    Journal Papers

  • "Speech Recognition Using Multiple Wearable Microphones for Multiparty Conversations," Shengke Lin, Takashi Tsunakawa, Masafumi Nishida, Masafumi Nishimura, Journal of Signal Processing, Vol.24, Issue 1, pp.19-29, 2020.1.
  • "Detecting breathing sounds in realistic Japanese telephone conversations and its application to automatic speech recognition,"
    Takashi Fukuda, Osamu Ichikawa, Masafumi Nishimura,
    Speech Communication, Vol.98, pp.95-103, 2018.3.
  • "日本語Wikificationにおけるアンカー抽出器および評価用コーパスの構築,"
    小谷亮太, 綱川隆司, 西田昌史, 西村雅史,
    情報処理学会論文誌, Vol.59, No.2, pp.306-314, 2018.2.
  • "Major depressive disorder discrimination using vocal acoustic features,"
    Takaya Taguchi, HirokazuTachikawaa, Kiyotaka Nemotoa, Masayuki Suzuki, Toru Nagano, Ryuki Tachibana, Masafumi Nishimura, Tetsuaki Arai,
    Journal of Affective Disorders, Vol.225, No.1 pp.214-220, 2018.
  • "嚥下音を用いた水分摂取量推定手法の研究,"
    小林悠一, 山田侑太郎, 西村雅史, 峰野博史, 飯田一郎,
    情報処理学会論文誌, Vol.57, No.2, February, 2016.
  • "Discriminative re-ranking for automatic speech recognition by leveraging invariant structures,"
    M.Suzuki, G.Kurata, M.Nishimura, N.Minematsu,
    Speech Communication, Vol 72, pp.208-217, September 2015.
  • "大語彙連続音声認識と音節N-best音声認識を用いたキーワード検索の高精度化,"
    長野 徹,倉田 岳人,鈴木 雅之,立花 隆輝,西村 雅史,
    情報処理学会論文誌, Vol.56, No.8, pp.1646-1656, August 2015.
  • "OpenEARを用いた音声による心理的ストレス検出の試み,"
    田口高也, 根本清貴,太刀川弘和,立花隆輝,西村雅史,新井哲明,朝田隆,
    精神医学, Vol.56, No.12, pp.1027-1034, December 2014.

  • *以下はIBM所属時のもの
  • "Leveraging Word Confusion Networks for Named Entity Modeling and Detection from Conversational Telephone Speech,"
    Gakuto Kurata, Nobuyasu Itoh, Masafumi Nishimura, Abhinav Sethy, Bhuvana Ramabhadran,
    Speech Communication, Vol.54, Issue 3, pp.491-502, March 2012.
  • "Acoustically Discriminative Language Model Training with Pseudo-hypothesis,"
    Gakuto Kurata, Abhinav Sethy, Bhuvana Ramabhadran, Ariya Rastrow, Nobuyasu Itoh, Masafumi Nishimura,
    Speech Communication, Vol.54, Issue 2, pp.219-228, February 2012.
  • "Corpus-based Text-to-Speech Front-end for Japanese,''
    T. Nagano, R. Tachibana, M. Nishimura,
    IEICE transactions on information and systems, D-II Vol. J93-D, No.10, pp.2096-2106, 2010, 10.
  • "Speech Input Method in Automobiles Reflecting Analysis on How Users Speak,"
    Kurata. G., Ichikawa, O.,Nishimura, M.,
    IEICE transactions on information and systems, D-II Vol, J93-D, No.10, pp.2107-2117, 2010, 10.
  • “Dynamic Features in the Linear-Logarithmic Hybrid Domain for Automatic Speech Recognition in a Reverberant Environment,"
    Ichikawa, O., Fukuda, T., Nishimura, M.,
    IEEE journal of selected topics in signal processing, Vol., 4, Isuue 5, 2010.
  • “Long-term spectro-temporal and static harmonic features for voice activity detection,”
    Fukuda, T., Ichikawa, O., Nishimura, M.,
    IEEE journal of selected topics in signal processing, Vol., 4, Issue 5, 2010.
  • "DOA Estimation with Local-Peak-Weighted CSP,"
    Ichikawa, O., Fukuda, T., Nishimura, M.,
    Trans. EURASIP, Volume 2010, Article ID 358729, 9 pages, 2010, May.
  • "Local peak enhancement for in-car speech recognition in noisy environment,"
    O.Ichikawa, T.Fukuda, M.Nishimura,
    IEICE Transactions on Information and Systems, Vol.E91D No.3, pp.635-639, 2008.
  • "Unsupervised Construction of Speech Recognition Lexicon from Speech and Text,"
    Gakuto Kurata, Shinsuke Mori, Nobuyasu Itoh, Masafumi Nishimura,
    Transactions of IPSJ, Vol.49, No.8, pp.2900-2909, 2008.
  • "Unsupervised Adaptation of a Speech Recognition System Using a Lecture-Related Corpus,"
    Gakuto Kurata, Shinsuke Mori, Masafumi Nishimura,
    IEICE Transactions on information and systems, Vol. J90-D, No.9, pp.2530-2540, 2007.
  • "Automatic Prosody Labeling using Multiple Models for Japanese,"
    R.Tachibana, T.Nagano, G.Kurata, M.Nishimura, N.Babaguchi,
    IEICE Transactions on Information and Systems, Vol. E90-D, No.11, pp. 1805-1812, 2007.
  • "Acoustic Model Adaptation Using First-Order Linear Prediction for Reverberant Speech”,
    T. Takiguchi, M. Nishimura, and Y. Ariki,
    IEICE Transactions on Information and Systems, Vol. E89-D, No. 3, pp. 908-914, 2006.
  • “An N-gram-based Approach to Phoneme and Accent Estimation for TTS,”
    Tohru Nagano, Shinsuke Mori, Masafumi Nishimura,
    Transactions of IPSJ, Vol.47, No.6, 2006.
  • "Simultaneous adaptation of echo cancellation and spectral subtraction for in-car speech recognition,"
    O.Ichikawa, M.Nishimura,
    IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences, Vol.E88-A No.7, pp.1732-1738, 2005.
  • "Sound source localization using a pinna-based Profile Fitting method,"
    O.Ichikawa, T.Takiguchi, M.Nishimura,
    IEICE Transactions on Information and Systems, Vol.E87-D No.5, pp.1138-1145, 2004.
  • "Improved HMM Separation for Distant-Talking Speech Recognition,"
    T.Takiguchi, M.Nishimura,
    IEICE Trnsactions on Information and Systems, Vol.E87-D, No.5, pp.1127-1137, 2004.
  • "Speech enhancement by Profile Fitting method,"
    O.Ichikawa, T.Takiguchi, M.Nishimura,
    IEICE Transactions on Information and Systems, Vol.E86-D No.3, pp.514-521, 2003.
  • "Large vocabulary spontaneous-speech recognition using a corpus of lectures,"
    M.Nishimura, N.Itoh,
    Electronics and Communications in Japan, Vol.86, No.9 , 2003.Sep.
  • "Large vocabulary spontaneous-speech recognition using a corpus of lectures,"
    Masafumi Nishimura, Nobuyasu Itoh,
    IEICE Transactions on Information and Systems, D-2, Vol.J83-D2, pp.2473-2480, 2000, 11.
  • "Word-based approach to large-vocabulary continuous speech recognition for Japanese,"
    Masafumi Nishimura, Nobuyasu Itoh, Kazutaka Yamasaki,
    Transactions of IPSJ, Vol.40, No.4, pp.1395-1403, 1999-4.
  • "Wavelet analysis for text-to-speech synthesis, " Mei Kobayashi, Masaharu Sakamoto, Takeshi Saito, Yasuhide Hashimoto,
    Masafumi Nishimura, Kazuhiro Suzuki,
    IEEE Circuits & Systems, Vol. 45, No. 8, Aug. 1998, pp. 1125-1129.
  • "A Word-based Japanese Language Model,"
    Nobuyasu Itoh, Masafumi Nishimura, Shiho Ogino, Kazutaka Yamasaki,
    Journal of Natural Language Processing, Vol.6, No.1, pp.9-28, Jan., 1999.
  • "A word-based Japanese dictation system,"
    Masafumi Nishimura, Nobuyasu Itoh,
    IEICE Transactions on Information and Systems, D-II, Vol. J81-D-II, No.1, pp.1-8, 1998.1.
  • "Word clustering for class-based language models,"
    Shinsuke Mori, Masafumi Nishimura, Nobuyasu Itoh, Transactions of IPSJ, Vol. 38, No.11, pp.2200-2208, 1997.
  • "Large-vocabulary Speech Recognition on a General-purpose Speech Processing Card,"
    Akihiro Kuroda, Masafumi Nishimura,
    Transactions of IPSJ, Vol. 35, No.8, pp.1549-1554, 1994.
  • "Speaker adaptation method for fenonic Markov model-based speech recognition,"
    Masafumi Nishimura,
    Systems and Computers in Japan, Vol.22, No.13, pp.47-58, 1991.
  • "Speaker Adaptation Method for Fenonic Markov Model-based Speech Recognition,"
    Masafumi Nishimura,
    IEICE Transactions on Information and Systems, D-II, Vol. J73-D-II, No.10, pp.1630-1638, 1990.
  • "Monosyllable Recognition by Using Intermediate Cumulative Distance and Normalized Distance Similarity,"
    Masafumi Nishimura, Yasuhiro Matsuda,
    Transactions of IPSJ, Vol. 27, No.1, pp.41-48, 1986.
  • International Conference Papers

  • "Analysis of Acoustic Features Affected by Conditions of the Vocal Tract," Masahiro Koto, Tomoki Hosoyama, Masafumi Nishimura, Masafumi Nishida, Yasuo Horiuchi, Shingo Kuroiwa, Proceedings of the NCSP2020, 1AM1-3-5, 2020.2.
  • "Estimation of Number of Chewing Strokes and Swallowing Events by Using LSTM-CTC and Throat Microphone," Muhammad Mehedi Billah,Taiju Abe, Akihiro Nakamura, Takato Saito, Daizo Ikeda, Hiroshi Mineno, Masafumi Nishimura, Proc. of IEEE GCCE2019, pp.944-945, 2019.10.
  • "Effects of Mounting Position on Throat Microphone Speech Recognition," Takahito Suzuki, Jun Ogata, Takashi Tsunakawa, Masafumi Nishida, Masafumi Nishimura, Proc. of IEEE GCCE2019, pp.897-898, 2019.10.
  • "Knowledge Distillation for Throat Microphone Speech Recognition," Takahito Suzuki, Jun Ogata, Takashi Tsunakawa, Masafumi Nishida, Masafumi Nishimura, Proc. of Interspeech2019, pp.461-465, 2019.9.
  • "Multimodal Behavior Analysis Towards Detecting Mild Cognitive Impairment: Preliminary Results on Gait and Speech," Kaoru Shinkawa, Akihiro Kosugi, Masafumi Nishimura, Miyuki Nemoto, Kiyotaka Nemoto, Tomoko Takeuchi, Yuriko Numata, Ryohei Watanabe, Eriko Tsukada, Miho Ota, Shinji Higashi, Tetsuaki Arai, Yasunori Yamada, MEDINFO 2019: Health and Wellbeing e-Networks for All, Vol. 264, pp. 343-347, 2019.8.
  • "Using Tablet-Based Assessment to Characterize Speech for Individuals with Dementia and Mild Cognitive Impairment: Preliminary Results," Aidan O. Hall, Kaoru Shinkawa, Akihiro Kosugi, Toshiro Takase, Masatomo Kobayashi, Masafumi Nishimura, Miyuki Nemoto, Ryohei Watanabe, Eriko Tsukada, Miho Ota, Shinji Higashi, Kiyotaka Nemoto, Tetsuaki Arai and Yasunori Yamada, Proc. of AIMI Joint Summits on Translational Science, pp. 34-43, 2019.5.
  • "Bottleneck Feature-Mediated DNN-Based Feature Mapping for Throat Microphone Speech Recognition," T. Suzuki, J. Ogata, T. Tsunakawa, M. Nishida, M. Nishimura, Proc. of APSIPA 2018, WE-A1-P.10, pp.1738-1741, 2018.11.
  • "Dialogue Breakdown Detection Based on Nonlinguistic Acoustic Information," M. Abe, T. Tsunakawa, M. Nishida and M. Nishimura, Proc. of IEEE 7th Global Conference on Consumer Electronics, pp.654-655, 2018.
  • "Dietary and Conversational Behavior Monitoring by Using Sound Information,"
    Jumpei Ando, Takato Saito, Satoshi Kawasaki, Masaji Katagiri, Daizo Ikeda, Hiroshi Mineno, Takashi Tsunakawa, Masafumi Nishida and Masafumi Nishimura,
    Proc. of NCSP 2018, pp.675-678, 2018.3.
  • "Conversational Speech Recognition Using Multiple Wearable Microphones,"
    Shengke Lin, Takashi Tsunakawa, Masafumi Nishida, and Masafumi Nishimura,
    Proc. of NCSP 2018, pp.363-366, 2018.3.
  • "Analysis and estimation of user’s motivation of conversation by using acoustic features," Ryota Togai, Motoki Abe, Takashi Tsunakawa, Masafumi Nishida and Masafumi Nishimura,
    Proc. of NCSP 2018, pp.678-682, 2018.3.
  • "DNN-based Feature Transformation for Speech Recognition Using Throat Microphone",
    Shengke Lin, T.Tsunakawa, M.Nishida, and M. Nishimura,
    Asia-Pacific Signal and Information Processing Association. pp.596-599, December. 2017.
  • Keynote Speech@ICCAI2017
    "Use of Sound Information for Supporting the Elderly and the Disabled,"
    Masafumi Nishimura,
    International conference on computing and applied informatics 2017, 2017.11.
  • "Deep Learning-Based Water-Intake Estimation Method Using Second Half of Swallowing Sound,"
    Yutaro Yamada, Takato Saito, Satoshi Kawasaki, Daizo Ikeda, Masaji Katagiri, Masafumi Nishimura, Hiroshi Mineno,
    Proc. 2017 IEEE 6th Global Conference on Consumer Electronics(GCCE2017), pp.847-848, 2017.
  • "A Deep-learning-based Method of Estimating Water Intake,"
    Yutaro Yamada, Takato Saito, Satoshi Kawasaki, Daizo Ikeda, Masaji Katagiri, Masafumi Nishimura, Hiroshi Mineno,
    The 12th IEEE International COMPSAC Workshop on E-Health Systems and Semantic Web (ESAS), 2017.7.
  • "Voice Activity Detection Using Throat and Lavalier Microphones for Multi-Party Conversations,"
    Y.Otaka, T.Tsunakawa, M.Nishida, M.Nishimura,
    NCSP2017, 2AM2-3-2, pp.369-372, 2017.3.
  • "A Study on Acoustic Features Related to Mental Disorders,"
    M.Fujiwara, T.Tsunakawa, M.Nishida, M.Nishimura, M.Suzuki, T.Nagano, R.Tachibana, T.Taguchi, K.Nemoto, H.Tachikawa,
    NSCP2017, 2AM1-3-3, pp.317-320, 2017.3.

  • *以下はIBM所属時のもの
  • "A Metric for Evaluating Speech Recognizer Output based on Human-Perception Model," Nobuyasu Itoh, Gakuto Kurata, Ryuki Tachibana, Masafumi Nishimura, Proc. of 16th Annual Conference on the International Speech Communication Association (Interspeech 2015).
  • "Regularized Feature-space Discriminative Adaptation for Robust ASR,"
    Takashi Fukuda, Osamu Ichikawa, Masafumi Nishimura, Steven J. Rennie, and Vaibhava Goel,
    Proc. of 15th Annual Conference on the International Speech Communication Association (Interspeech 2014), pp.2185-2188, September 2014, Singapore.
  • "Channel-mapping for speech corpus recycling,"
    O. Ichikawa, S.J. Rennie, T. Fukuda, M. Nishimura,
    Acoustics, Speech and Signal Processing (ICASSP), 2013 IEEE International Conference on, pp. 7160-7164.
  • "Disicriminative Reranking for LVCSR Leveraging Invariant Structure,"
    Masayuki Suzuki, Gakuto Kurata, Masafumi Nishimura, Nobuaki Minematsu,
    INTERSPEECH 2012, Sep., 2012.
  • "Model-based noise reduction leveraging frequency-wise confidence metric for in-car speech recognition,"
    Osamu Ichikawa, Steven Rennie, Takashi Fukuda, Masafumi Nishimura,
    SP-P16, ICASSP 2012, March 2012.
  • "Continuous Digits Recognition Leveraging Invariant Structure,"
    Masayuki Suzuki, Gakuto Kurata, Masafumi Nishimura, Nobuaki Minematsu,
    INTERSPEECH 2011, Aug., 2011.
  • "Breath-detection-based Telephony Speech Phrasing,"
    Takashi Fukuda, Osamu Ichikawa, Masafumi Nishimura,
    INTERSPEECH 2011, Aug., 2011.
  • "Agglomerative Hierarchical Clustering of Emotions in Speech Based on Subjective Relative Similarity,"
    Ryoichi Takashima, Tohru Nagano, Ryuki Tachibana, Masafumi Nishimura,
    INTERSPEECH 2011, Aug., 2011.
  • "Combining feature space discriminative training with long-term spectro-temporal features for noise-robust speech recognition,"
    Takashi Fukuda, Osamu Ichikawa, Masafumi Nishimura,
    INTERSPEECH 2011, Aug., 2011.
  • "Acoutic Model Training with Detecting Transcription Errors in the Training Data,"
    Gakuto Kurata, Nobuyasu Itoh, Masafumi Nishimura,
    INTERSPEECH 2011, Aug., 2011.
  • "Training of Error-Corrective Model for ASR without Using Audio Data,"
    Gakuto Kurata, Nobuyasu Itoh, Masafumi Nishimura,
    Proc. of ICASSP 2011, pp.5572-5575, May, 2011.
  • "Named Entity Recognition from Conversational Telephone Speech Leveraging Word Confusion Networks for Training and Recognition,”
    Gakuto Kurata, Nobuyasu Itoh, Masafumi Nishimura, Abhinav Sethy, Bhuvana Ramabhadran,
    Proc. of ICASSP 2011, pp.5576-5579, May, 2011.
  • “Speech Synthesis by Modeling Harmonics Structure with Multiple Function”,
    Nakashika, T., Tachibana, R., Nishimura, M., Takiguchi, T., Ariki, Y,
    INTERSPEECH 2010, pp.295-948, Sep., 2010.
  • “Improved voice activity detection using static harmonic features,”
    Fukuda, T., Ichikawa, O., Nishimura, M.,
    International conference on acoustic, speech, and signal processing (ICASSP), pp. 4482-4485, 2010, March.
  • “Dynamic Features in the Linear Domain for Robust Automatic Speech Recognition in a Reverberant Environment”,
    Osamu Ichikawa, Takashi Fukuda, Masafumi Nishimura,
    Interspeech 2009, Sep. 2009
  • "Japanese Pitch Conversion for Voice Morphing Based on Differential Modeling,"
    Ryuki Tachibana, Zhiwei Shuang, Masafumi Nishimura,
    InterSpeech 2009, Sep. 2009.
  • “Acoustically Discriminative Training for Language Models”,
    Gakuto KURATA, Nobuyasu ITOH, Masafumi NISHIMURA,
    Proc. Of ICASSP 2009, Apri. 2009
  • “Local Peak Enhancement Combined with Noise Reduction Algorithms for Robust Automatic Speech Recognition in Automobiles,”
    O.Ichikawa, T.Fukuda, M.Nishimura,
    IEEE ICASSP 2008, pp.4865-4868, 2008.
  • "Improving Phoneme and Accent Estimation by Leveraging a Dictionary for a Stochatic TTS Front-end,"
    T.Nagano, R.Tachibana, N. Itoh, and M.Nishimura,
    Proc.,IEEE ICASSP 2008, pp.4689-4692, 2008.
  • "Phone-duration-dependent Long-term Dynamic Features for Stochastic Model-based Voice Activity Detection,"
    T.Fukuda, O.Ichikawa, M.Nishimura,
    Proc of Interspeech 2008, pp.1293-1296, 2008.
  • "Short- and Long-term Dynamic Features for Robust Speech Recognition,"
    T.Fukuda, O.Ichikawa, M.Nishimura,
    Proc of Interspeech 2008, pp.2262-2265, 2008.
  • "Preliminary Experiments toward Automatic Generation of New TTS Voices from Recorded Speech Alone,"
    R.Tachibana, T.Nagano, G.Kurata, M.Nishimura, N.Babaguchi,
    Proc. of INTERSPEECH, 2007.
  • "Unsupervised Lexicon Acquisition from Speech and Text, "
    G.KURATA, S.MORI, N.ITOH, M.NISHIMURA,
    Proc. of ICASSP 2007, Vol.4, pp.421-424, 2007.
  • "Unsupervised Adaptation of a Stochastic Language Model Using a Japanese Raw Corpus,"
    Gakuto KURATA, Shinsuke MORI, Masafumi NISHIMURA
    ICASSP 2006.6.
  • "Simultaneous adaptation of echo cancellation and spectral subtraction for in-car speech recognition,"
    Osamu Ichikawa and Masafumi Nishimura,
    Proc. of European Conference on Speech Communication and Technology (EuroSpeech / InterSpeech) 2005, pp.2293-2296, 2005.
  • "A Stochastic Approach to Phoneme and Accent Estimation,"
    Tohru NAGANO, Shinsuke MORI, Masafumi NISHIMURA
    EuroSpeech 2005
  • "Acoustic Model Adaptation using First Order Prediction for Reverberant Speech," T.Takiguchi, M.Nishimura, Proc. IEEE International Conf. on Acoustics, Speech and Signal Processing, pp.869-872. 2004.
  • "Language Model Adaptation Using Word Clustering,"
    Shinsuke MORI, Masafumi NISHIMURA, Nobuyasu ITOH
    Proc. of EuroSpeech 2003, pp.425-428, 2003.
  • "Reverberant Speech Recognition using First-Order Linear Prediction,"
    T.Takiguchi, M.Nishimura,
    Proc. of International Congress on Acoustics, pp.2829-2830. 2003.
  • "Sound source localization using a pinna-based Profile Fitting method,"
    O.Ichikawa, T.Takiguchi, M.Nishimura,
    International Workshop on Acoustic Echo and Noise Control(IWAENC), pp.263-266, 2003.
  • "An automatic sentence boundary detector based on a structured language model,"
    S.Mori, M.Nishimura and N.Itoh,
    Proc. of ICSLP 2002., pp.921-924, Sep. 2002.
  • "Improvement of a Structured Language Model: Arbori-context Tree,"
    Shinsuke MORI, Masafumi NISHIMURA, Nobuyasu ITOH
    Proc. of EuroSpeech 2001, pp. 713-716, 2001.
  • "A Stochastic Parser Based on a Structural Word Prediction Model,"
    Shinsuke MORI, Masafumi NISHIMURA, Nobuyasu ITOH, Shiho OGINO, Hideo WATANABE
    Proc. of Coling 2000, pp. 558-564, 2000.
  • "Integration of HMM composition and a microphone array for overlapping speech recognition,"
    T.Takiguchi, M.Nishimura,
    Workshop on Hands-free speech communication, pp.127-130, 2001.
  • "A method for sytle adaptation to spontaneous speech by using a semi-linear interpolation technique,"
    N.Itoh, M.Nishimura,
    Proc of 6th ICSLP, Oct, 2000.
  • "Recognizing overlapping speech by using HMM composition,"
    T.Takiguchi, M.Nishimura,
    The seventh Western Pacific Regional Acoustics Conference, 2000.
  • "Word Clustering for a Word Bi-gram Model,"
    Shinsuke Mori, Masafumi Nishimura, Nobuyasu Itoh
    ICSLP 1998
  • "HMM-based speech recognition using dynamic spectral feature,"
    Masafumi Nishimura,
    IEEE ICASSP'89, S6.12, 1989.
  • "Speaker adaptation method for HMM-based speech recognition,"
    Masafumi Nishimura and Kazuhide Sugawara,
    IEEE ICASSP'88, S5.7, 1988.
  • "HMM-based speech recognition using multi-dimensional multi-labeling,"
    Masafumi Nishimura and Koichi Toshioka,
    IEEE ICASSP'87, 27.11, 1987.
  • "Speaker adaptation for a hidden Markov model,"
    Kazuhide Sugawara, Masafumi Nishimura and Akihiro Kuroda,
    IEEE ICASSP'86, 49.11, 1986.
  • "Isolated word recognition using HMM with duration distribution,"
    Masafumi Nishimura and Masakai Okochi,
    ICA-12, A1-8, 1986.
  • "Isolated word recognition using hidden Markov models,"
    Kazuhide Sugawara, Masafumi Nishimura Koichi Toshioka Masaaki Okochi and Toyohisa Kaneko,
    IEEE ICASSP'85, 1.1, 1985.
  • "A Method for recognizing Japanese monosyllables by using intermediate cumulative distance,"
    Yasuhiro Matsuda, Shu Tezuka, Mitsuhiko Kanoh, Masafumi Nishimura and Toyohisa Kaneko,
    IEEE ICASSP'84, 9.3, 1984.
  • Chapters in Books

  • "IBM's Japanese Dictation System,"
    Masafumi Nishimura
    Spoken Language Systems, Chapter2, pp.47-58, Ohmusha/IOS Press, 2005. ISBN 4-274-90637-X.
  • "Wavelet Analysis for a Text-to-speech System,"
    M.Kobayashi, M.Sakamoto, T.Saitoh, M.Nishimua,
    Wavelets and their applications, pp.75-100, SIAM, Philadelphia, PA, 1998.
  • "Wavelet Analysis of Speech Signals",
    M.Kobayashi, M.Sakamoto, T.Saitoh, M.Nishimura
    Approximation Theory VIII, Vol.2:Wavelets and Multilevel Approximation, pp209-215, Academic Press, NY, 1995
  • Patents and Patent Applications

  • [1] 評価装置、評価方法、及び評価プログラム (出願年月日]2019年8月27日)
    特願2019-154876
  • [2]. 嚥下音判定装置及び嚥下音判定方法 ([出願年月日]2017年9月1日)
    特願2017-168705
  • [3]. 嚥下情報提示装置 ([出願年月日]2016年7月11日)
    特開2018-7723

  • *以下はIBM所属時のもの
  • [1] "SPEECH ROCOGNITION SYSTEM," 1997-06-13, Pat. no. 2662120, Japan
  • [2] "A METHOD FOR CONTROLING DICTATION-STYLE MODEL," 2006-03-17, Pat. no. 3782943, Japan
  • [3] "A METHOD FOR PREDICTING DISFLUENCY WORDS BY N-GRAM MODEL," 2005-12-07, Pat. no. ZL00135969.X, China
  • [4] "A METHOD FOR PREDICTING DISFLUENCY WORDS BY N-GRAM MODEL," 2003-05-09, Pat. no. 3426176, Japan
  • [5] “Adaptation of Acoustic Prototype Vectors in a Speech Recognition System,” 1991-09-03, Pat. No. 5046099, United States
  • [6] "A PITCH SYNCHRONOUS OVERLAP-ADD METHOD BASED ON GLOTTAL CLOSURE INSTANTS," 2000-07-28, Pat. no. 3093113, Japan
  • [7] "HMM BASED SPECH RECOGNITION METHOD USING STATIC AND DYNAMIC FEATURES," 1994-12-26, Pat. no. 1892342, Japan
  • [8] "METHOD OF SPEECH MODELLING AND A SPEECH RECOGNIZER," 1999-04-14, Pat. no. 69324428.3, Germany
  • [9] "METHOD OF SPEECH MODELLING AND A SPEECH RECOGNIZER," 1999-04-14, Pat. no. 590925, France
  • [10] "METHOD OF SPEECH MODELLING AND A SPEECH RECOGNIZER," 1999-04-14, Pat. no. 590925, United Kingdom
  • [11] “METHOD, APPARATUS, COMPUTER SYSTEM AND STORAGE MEDIUM FOR SPEECH RECOGNITION,” 2005-07-12, Pat. No. 6917910, United States
  • [12] "SPEAKER ADAPTATION FOR HMM BASED SPEECH RECOGNITION," 1992-08-11, Pat. no. 1689273, Japan
  • [13] "SPEAKER ADAPTATION METHOD FOR VQ CODE BOOK," 1995-02-24, Pat. no. 1906392, Japan
  • [14] “SPEECH RECOGNITION APPARATUS AND METHOD UTILIZING A LANGUAGE MODEL PREPARED FOR EXPRESSIONS UNIQUE SPONTANEOUS SPEECH,” 2006-01-10, Pat. no. 6985863, United States
  • [15] “SPEECH RECOGNITION BY CONCATENATING FENONIC ALLOPHONE HIDDEN MARKOV MODELS IN PARALLEL AMONG SUBWORDS,” 1996-03-26, Pat. No. 5502791, United States
  • [16] "SPEECH RECOGNITION METHOD," 1989-06-27, Pat.no. 1256562, Canada
  • [17] "SPEECH RECOGNITION METHOD," 1991-09-18, Pat.no. 3773039808, Germany
  • [18] "SPEECH RECOGNITION METHOD," 1991-09-18, Pat. no. 243009, France
  • [19] "SPEECH RECOGNITION METHOD," 1991-09-18, Pat. no. 243009, United Kingdom
  • [20] "SPEECH RECOGNITION METHOD," 1991-09-18, Pat. no. 243009, Italy
  • [21] "SPEECH RECOGNITION METHOD," 1992-08-11, Pat. no. 1689246, Japan
  • [22] "SPEECH RECOGNITION METHOD," 1996-04-09, Pat. no. 2044703, Japan
  • [23] “SPEECH RECOGNITION METHOD,” 1989-05-09, Pat.no.4829577, United States
  • [24] "SPEECH RECOGNITION SYSTEM USING MARKOV MODELS," 1992-11-25, Pat. no. 3876207208, Germany
  • [25] "SPEECH RECOGNITION SYSTEM USING MARKOV MODELS," 1992-11-25, Pat. no. 312209, France
  • [26] "SPEECH RECOGNITION SYSTEM USING MARKOV MODELS," 1992-11-25, Pat. no. 312209, United Kingdom
  • [27] “SPEECH RECOGNITION SYSTEM USING MARKOV MODELS HAVING INDEPENDENT LABEL OUPUT SETS,” 1991-07-09, Pat.no.5031217, United States
  • [28] "SPEECH ROCOGNITION," 1998-04-01, Pat. no. 69224953.2, Germany
  • [29] "SPEECH ROCOGNITION," 1998-04-01, Pat. no. 535909, France
  • [30] "SPEECH ROCOGNITION," 1998-04-01, Pat. no. 0535909, United Kingdom
  • [31] “SPEECH ROCOGNITION SYSTEM HAVING AN INTEFACE TO A HOST COMPUTER BUS FOR DIRECT ACCESS TO THE HOST MEMORY,” 1994-10-04, Pat. No.5353377, United States
  • [32] “SPEECH SYNTHESIS USING GLOTTAL CLOSURE INSTANTS DETERMINED FROM ADAPTIVELY-THRESHOLDED WAVELET TRANSFORMS,” 1997-09-23, Pat.no.5671330, United States
  • [33] “SYSTEM INSERTION APPARATUS AND METHOD,” 2004-08-17, Pat.no.6778958, United States
  • [34] "VOICE RECOGNITION APPARATUS," 1995-07-25, Pat. no. 1336458, Canada
  • [35] "WORD-BASED JAPANESE DICTATION SYSTEM," 2000-10-20, Pat. no. 3121530, Japan
  • [36] “SPEECH RECOGNITION METHOD,” 1991-09-17, Pat.no. 5050215, United States
  • [37] "SPEECH RECOGNITION METHOD USING A TRAINABLE HMM-NETWORK," 1996-04-25, Pat. no. 2048523, Japan
  • [38] "SPEECH RECOGNITION SYSTEM," 1994-07-20, Pat. no. 69010722.6, Germany
  • [39] "SPEECH RECOGNITION SYSTEM," 1994-07-20, Pat. no. 388067, France
  • [40] "SPEECH RECOGNITION SYSTEM," 1994-07-20, Pat. no. 388067, United Kingdom
  • [41] "SYSTEM, PROGRAM, AND CONTROL METHOD FOR SPEECH SYNTHESIS," 2009-01-23, Pat. no. 4247564, Japan
  • [42] "REVERBERANT SPEECH RECOGNITION BASED ON MODEL COMPENSATION APPROACH," 2006-08-04, Pat. no. 3836815, Japan
  • [43] "APPARATUS, METHOD, AND PROGRAM FOR SUPPORTING SPEECH INTERFACE DESIGN," 2008-07-18, Pat. no. 4156639, Japan
  • [44] "A METHOD TO DESIGN THE SHAPE OF OUTER-EAR SUITABLE FOR SOUND SOURCE LOCALIZATION," 2007-08-17, Pat. no. 3999689, Japan
  • [45] "CONTROLS FOR AUTOMATIC-PUNCTUATING FUNCTION," 2001-09-14, Pat. no. 3232289, Japan
  • [46] ”SPEECH RECOGNITION SYSTEM AND PROGRAM THEREOF,” 2008-07-22, Pat.no.7403896, United States
  • [47] "SPEECH RECOGNITION BY FRAME-WISE SELECTION OF THE MODEL UNDER THE RAPID CHANGE OF NOISE," 2007-12-28, Pat. no. 4061094, Japan
  • [48] "SPEECH RECORDING METHOD FOR COURT REPORT," 2008-02-22, Pat. no. 4082611, Japan
  • [49] “SYSTEMS AND METHODS FOR NATURAL SPOKEN LANGUAGE WORD PREDICTION AND SPEECH RECOGNITION,” 2008-04-15, Pat.no. 7359852, United States
  • [50] "STRUCTURAL LANGUAGE MODELING BASED ON DEPENDENCY," 2008-04-04, Pat. no. 4105841, Japan
  • [51] "LOW-COST METHOD FOR DETERMINING FILTER COEFFICIENT IN DEREVERBERATION," 2008-04-11, Pat. no. 4107613, Japan
  • [52] "SYSTEM FOR SUPPORTING TEXT-TO-SPEECH," 2008-05-30, Pat. no. 4129989, Japan
  • [53] "MICROPHONE-ARRAY BASED NOISE SUPPRESSION METHOD," 2008-10-03, Pat. no. 4195267, Japan
  • [54] "CONTEXT TREE FOR TREE-STRUCTURED HISTORY," 2008-11-14, Pat. no. 4215418, Japan
  • [55] “SPEECH RECOGNITION APPARATUS, SPEECH RECOGNITION APPARATUS AND PROGRAM THEREOF,” 2009-1-13, Pat.no. 7478041, United States.
  • [56] “WORD PREDICTING METHOD, VOICE RECOGNITION METHOD, AND VOICE RECOGNITION APPARATUS AND PROGRAM USING THE SAME METHODS,” 2009-01-20, Pat. No. 7480612, United States
  • [57] “SIGNAL ENHANCEMENT VIA NOISE REDUCTION FOR SPEECH RECOGNITION,” 2009-05-12, Pat. No. 7533015, United States
  • [58] “SIGNAL ENHANCEMENT VIA NOISE REDUCTION FOR SPEECH RECOGNITION,” 2011-02-22, Pat. No. 7895038, United States
  • [59] "SPEECH RECOGNITION SYSTEM AND METHOD," 2011-08-26, Pat. No. 4808764, Japan
  • [60] "RECORDING SYSTEM WITH IMPROVED SUPPRESSION OF INTERFERING TALKER," 2012-01-20, Pat. No. 4906908, Japan
  • [61] "METHOD AND SYSTEM FOR POSITION DETECTION OF A SOUND SOURCE," 2012-04-24, Pat. No. 8165317, United States
  • [62] "SYSTEM, METHOD, AND PROGRAM PRODUCT FOR PROCESSING SPEECH RATIO DIFFERENCE DATA VARIATIONS IN A CONVERSATION BETWEEN TWO PERSONS," 2012-04-24, Pat. No. 8165874, United States
  • [63] SYSTEM FOR PROCESSING VOICE DATA IN CONVERSATION BETWEEN TWO PERSONS, AND METHOD AND PROGRAM PRODUCT G. Kurata, M. Nishimura Japan Patent 5088741
  • [64] SYSTEM, METHOD AND PROGRAM FOR SPEECH PROCESSING O. Ichikawa, T. Fukuda, M. Nishimura Japan Patent 5089295
  • [65] FEATURE EXTRACTOR FOR ROBUST AUTOMATIC SPEECH RECOGNITION IN REVERBERANT AND NOISY ENVIRONMENT O. Ichikawa, T. Fukuda, M. Nishimura Japan Patent 5315414
  • [66] FEATURE EXTRACTOR FOR ROBUST AUTOMATIC SPEECH RECOGNITION IN REVERBERANT AND NOISY ENVIRONMENT O. Ichikawa, T. Fukuda, M. Nishimura UK Patent 2485926
  • [67] SPEECH FEATURE EXTRACTOR APPARATUS, SPEECH FEATURE EXTRACTION METHOD, AND SPEECH FEATURE EXTRACTION PROGRAM O. Ichikawa, T. Fukuda, M. Nishimura US Patent 8468016
  • [68] SPEECH COLLECTING METHOD, SYSTEM AND PROGRAM PRODUCT T. Fukuda, O. Ichikawa, M. Nishimura Japan Patent 5339501
  • [69] FEATURE EXTRACTOR FOR ROBUST AUTOMATIC SPEECH RECOGNITION IN REVERBERANT AND NOISY ENVIRONMENT O. Ichikawa, T. Fukuda, M. Nishimura Korea Patent 1332143
  • [70] Information Processing Device, Large Vocabulary Continuous Speech Recognition Method, and Program Gakuto Kurata, Masayuki Suzuki, Masafumi Nishimura US Patent App. 13/744,963
  • [71] Speech processing based on time series of maximum values of cross-power spectrum phase between two consecutive speech frames Osamu Ichikawa, Masafumi Nishimura US Patent 8,566,084
  • [72] FEATURE EXTRACTOR FOR ROBUST AUTOMATIC SPEECH RECOGNITION IN REVERBERANT AND NOISY ENVIRONMENT O. Ichikawa, T. Fukuda, M. Nishimura China Patent ZL201080038121.5
  • [73] VOICE ACTIVITY DETECTION SYSTEM, METHOD, AND PROGRAM PRODUCT T. Fukuda, O. Ichikawa, M. Nishimura Japan Patent 5505896
  • [74] TARGET VOICE EXTRACTION METHOD, APPARATUS AND PROGRAM PRODUCT T. Fukuda, O. Ichikawa, M. Nishimura US Patent 8762137
  • [75] SYSTEM, METHOD AND PROGRAM FOR SPEECH PROCESSING T. Fukuda, O. Ichikawa, M. Nishimura US Patent 8812312
  • [76] APPARATUS, METHOD, AND PROGRAM FOR DETECTING BREATH EVENT INCLUDED IN SPEECH T. Fukuda, M. Nishimura Japan Patent 5647455
  • Copyright(c) 2014 静岡大学情報学部西村/西田研究室 All Rights Reserved. Design by http://f-tpl.com