Journal Paper

• Sadaoki Furui, Masanobu Nakamura, Tomohisa Ichiba, Koji Iwano. Analysis and recognition of spontaneous speech using Corpus of Spontaneous Japanese, Speech Communication, Vol. 47, pp. 208-219, Sept. 2005.
• Zhipeng Zhang, Toshiaki Sugimura, Sadaoki Furui. Tree-Structured Clustering Methods for Piecewise Linear-Transformation-Based Noise Adaptation, IEICE Trans.Inf.&Syst., Vol. E88-D, No. 9, pp. 2168-2176, Sept. 2005.
• Jen-Tzung Chien, Sadaoki Furui. Predictive hidden Markov model selection for speech recognition, IEEE Transactions on speech and audio processing, Vol. 13, No. 3, pp. 377-387, July 2005.
• Sadaoki Furui. Recent progress in corpus-based spontaneous speech recognition, IEICE Transactions on Information and Systems, Vol. E.88-D, No. 3, pp. 366-375, Mar. 2005.
• Sadaoki Furui. Toward Robust Speech Recognition and Understanding, Journal of VLSI Signal Processing 41,Springer Science+Business Media,INC., pp. 245-254, 2005.  Official location  

Book

• Koji Iwano, Taro Miyazaki, Sadaoki Furui. Multimodal speaker verification using ear image features extracted by PCA and ICA, AVBPA 2005,LNCS 3546, Audio-and Video-Based Biometric Person Authentication, Takeo Kanade, Anil Jain, Nalini K. Ratha(Eds.), Springer-Verlag, Berlin and Heidelberg, Germany, Vol. ISBN 3-540-27887-7, pp. 588-596, July 2005.  Official location  
• Satoshi Tamura, Koji Iwano, Sadaoki Furui. A robust multimodal speech recognition method using optical flow analysis, Spoken Multimodal Human-Computer Dialogue in Mobile Environments,Springer,Netherlands, Spoken Multimodal Human-Computer Dialogue in Mobile Environments, W.Minker, Dirk Buhler and Laila Dybkjaer (Eds.), Springer, Dordrecht, pp. 37-53, Jan. 2005.  Official location  
• Sadaoki Furui. Speech recognition technology in multimodal/ubiquitous computing environments, Spoken Multimodal Human-Computer Dialogue in Mobile Environments,Springer,Netherlands, Spoken Multimodal Human-Compurer Dialogue in Mobile Environments, W.Minker, Dirk Buhler and Laila Dybkjaer(Eds.),Springer, Dordrecht, pp. 13-36, Jan. 2005.
• Koji Iwano, Takahiro Seki, Sadaoki Furui. Noise Robust Speech Recognition Using Prosodic Information, DSP for In-Vehicle and Mobile Systems,Springer,New York, DSP for In-Vehicle and Mobile Systems, Huseyin Abut, John H.L.Hansen and Kazuya Takeda(Eds.), Springer Verlag, New York, pp. 139-152, Jan. 2005.

International Conference (Reviewed)

• Edward Whittaker, Julien Hamonic, Sadaoki Furui. A Unified Approach to Japanese and English Question Answering, NTCIR-5 Workshop Meeting,Tokyo, pp. 552-555, Dec. 2005.
• Edward Whittaker, Pierre Chatain, Sadaoki Furui. TREC2005 Question Answering Experiments at Tokyo Institute of Technology, Text Retrieval Conference(TREC2005),Gatherburg, Nov. 2005.
• Edward Whittaker, Sadaoki Furui, Dietrich Klakow. A Statistical Classification Approach to Question Answering Using Web Data, International Conference on Cyberworlds, Singapore, pp. 421-428, Nov. 2005.
• Sadaoki Furui. 50 Years of Progress in Speech and Speaker Recognition, SPECOM 2005,Patras, pp. 1-9, Oct. 2005.
• Arnar Thor Jensson, Edward W. D. Whittaker, Koji Iwano, Sadaoki Furui. Language model adaptation for resource deficient languages using translated data, Interspeech2005, pp. 1329-1332, Sept. 2005.
• Javier Latorre, Koji Iwano, Sadaoki Furui. Cross-language synthesis with a polyglot synthesizer, Interspeech2005, pp. 1477-1480, Sept. 2005.
• Taichi Asami, Koji Iwano, Sadaoki Furui. Stream-weight optimization by LDA and adaboost for multi-stream speaker verification, Interspeech2005, pp. 2185-2188, Sept. 2005.
• Sadaoki Furui, Tomohisa Ichiba, Takahiro Shinozaki, Edward W.D.Whittaker, Koji Iwano. Cluster-based modeling for ubiquitous speech recognition, Interspeech2005, pp. 2865-2868, Sept. 2005.
• Masanobu Nakamura, Koji Iwano, Sadaoki Furui. Analysis of spectral space reduction in spontaneous speech and its effects on speech recognition performances, Interspeech2005, pp. 3381-3384, Sept. 2005.
• Sadaoki Furui, Masanobu Nakamura, Tomohisa Ichiba, Koji Iwano. Why is the recognition of spontaneous speech so hard ?, 8th International Conference on Text, Speech and Dialogue(TSD2005), Karlovy Vary, Czech Republic, pp. 9-22, Sept. 2005.  Official location  
• Sadaoki Furui. Spontaneous Speech Recognition and Summarization, The Second Baltic Conference on HUMAN LANGUAGE TECHNOLOGIES, pp. 39-50, Apr. 2005.
• Makoto Hirohata, Yousuke Shinnaka, Koji Iwano, Sadaoki Furui. Sentence extraction-based presentation summarization techniques and evaluation metrics, ICASSP2005, IEEE ICASSP2005, IEEE, Vol. SP, No. P16.14, pp. I-1065-1068, Mar. 2005.
• Satoshi Tamura, Koji Iwano, Sadaoki Furui. A Stream-weight optimization method for multi-stream HMMs based on likelihood value normalization, ICASSP2005, IEEE ICASSP2005, IEEE, Vol. SP, No. P5.2, pp. I-469-472, Mar. 2005.
• Zhipeng Zhang, Sadaoki Furui. Noisy speech recognition based on robust end-point detection and model adaptation, ICASSP2005, IEEE ICASSP2005, IEEE, Vol. SP, No. P4.7, pp. I-441-444, Mar. 2005.
• Javier Latorre, Koji Iwano, Sadaoki Furui. Polyglot synthesis using a mixture of monolingual corpora, ICASSP2005, IEEE ICASSP2005, IEEE, No. SP-L1.1, pp. I-1-4, Mar. 2005.

International Conference (Not reviewed / Unknown)

• Agnieszka Betkowska, Koichi Shinoda, Sadaoki Furui. Model optimization for noise discrimination in home environment, Symposium on Large-Scale Knowledge Resources (LKR2005), Proc. Symposium on Large-Scale Knowledge Resources (LKR2005), pp. 167-170, Mar. 2005.
• Sadaoki Furui. 21st century COE program Framework for systematization and application of large-scale knowledge resources, Symposium on Large-Scale Knowledge Resources(LKR2005), pp. 3-8, Mar. 2005.
• Koichi Shinoda, Nguyen Huu Bach, Sadaoki Furui, Naoki Kawai. Scene recognition using Hidden Markov Models for video database, Symposium on Large-Scale Knowledge Resources(LKR2005), Proc. Symposium on Large-Scale Knowledge Resources(LKR2005), pp. 107-110, Mar. 2005.
• Edward Whittaker, Sadaoki Furui. Question Answering as a Classification Task, Symposium on Large-Scale Knowledge Resourses(LKR2005),, pp. 39-42, Mar. 2005.
• Javier Latorre, Koji Iwano, Sadaoki Furui. Speaker adaptable multilingual synthesis, Symposium on Large-Scale Knowledge Resources (LKR2005), pp. 235-238, Mar. 2005.
• Satoshi Tamura, Koji Iwano, Sadaoki Furui. Toward robust multimodal speech recognition, Symposium on Large Scale Knowledge Resources (LKR2005), pp. 163-166, Mar. 2005.
• Sadaoki Furui, Makoto Hirohata, Yousuke Shinnaka, Koji Iwano. Sentence extraction-based automatic speech summarization and evaluation techniques, Symposium on Large-Scale Knowledge Resources(LKR2005), pp. 33-38, Mar. 2005.

Domestic Conference (Not reviewed / Unknown)

• 浅見 太一, Koji Iwano, Sadaoki Furui. マルチストリーム話者照合におけるブースティングに基づく闘値最適化法の検討, 電子情報通信学会 技術研究報告, Vol. SP2005, No. 90, pp. 1-6, Dec. 2005.
• Ryuta Nakagawa, Koji Iwano, Sadaoki Furui. 超並列計算機を用いた入力音声の変動に頑健な音声対話システムの検討, 電子情報通信学会 技術研究報告, Vol. SP2005, No. 105, pp. 1-6, Dec. 2005.
• Javier Latorre, Koji Iwano, Sadaoki Furui. HMM-Based Speaker Adaptable Polyglot Synthesizer-Development and Evaluation-, 電子情報通信学会 技術研究報告, Vol. SP2005, No. 132, pp. 127-132, Dec. 2005.
• Arnar Jensson, Edward Whittaker, Koji Iwano, Sadaoki Furui. Improvement of language model adaptation using machine-translated text, 日本音響学会2005年秋季研究発表会, 日本音響学会2005年秋季講演論文集, 日本音響学会, No. 2-1-4, pp. 43-44, Sept. 2005.
• Ryuta Nakagawa, 小林唯, 小林隆二, Koichi Shinoda, SADAOKI FURUI. 音声と手書き文字の同時入力によるインターフェースの検討, 日本音響学会2005年秋季研究発表会, 日本音響学会2005年秋季講演論文集, 日本音響学会, No. 1-7-11, pp. 13-14, Sept. 2005.
• Masanobu Nakamura, Koji Iwano, SADAOKI FURUI. 読み上げ音声に対する話し言葉音声の言語的特徴の分析, 日本音響学会2005年秋季研究発表会, 日本音響学会2005年秋季講演論文集, 日本音響学会, No. 3-6-10, pp. 347-348, Sept. 2005.
• Ryuta Nakagawa, Koji Iwano, SADAOKI FURUI. 超並列デコーダと逐次適応を用いた音声対話システム, 日本音響学会2005年秋季研究発表会, 日本音響学会2005年秋季講演論文集, 日本音響学会, Vol. 〔1-7-8〕, pp. 7-8, Sept. 2005.
• 小島要, Koji Iwano, SADAOKI FURUI. マルチバンド音声認識における尤度重み推定法の検討, 日本音響学会2005年秋季研究発表会, 日本音響学会2005年秋季講演論文集, 日本音響学会, No. 2-7-4, pp. 65-66, Sept. 2005.
• 浅見太一, Koji Iwano, Sadaoki Furui. マルチストリーム話者照合におけるブースティングを用いた閾値の最適化, 日本音響学会2005年秋季研究発表会, 日本音響学会2005年秋季講演論文集, 日本音響学会, No. 3-7-13, pp. 127-128, Sept. 2005.
• Joanna Mrozinski, Pierre Chatain, Edward Whittaker, Sadaoki Furui. Automatic sentence segmentation for speech summarization, 日本音響学会2005年秋季研究発表会, 日本音響学会2005年秋季講演論文集, 日本音響学会, Vol. 〔3-7-9〕, pp. 119-120, Sept. 2005.
• 赤川達也, Koji Iwano, SADAOKI FURUI. HMMを用いた話し言葉音声合成に関する検討, 日本音響学会2005年秋季研究発表会, 日本音響学会2005年秋季講演論文集, 日本音響学会, No. 3-6-17, pp. 361-362, Sept. 2005.
• Javier Latorre, Koji Iwano, Sadaoki Furui. New approach to cross-language synthesis, 日本音響学会2005年秋季研究発表会, 日本音響学会2005年秋季講演論文集, 日本音響学会, Vol. 〔3-6-12〕, pp. 351-352, Sept. 2005.
• Hiroaki Okamoto, Takashi Kobayashi, Satoshi Naoi, HARUO YOKOTA, Sadaoki Furui. 講義講演シーン検索における音声データの利用, 電子情報通信学会 技術研究報告, Vol. DE2005, No. 1007, pp. 1-6, July 2005.
• Koji Iwano, 広畑誠, 新中庸介, SADAOKI FURUI. 重要文抽出による音声自動要約手法とその客観的評価法についての検討, 電子情報通信学会 技術研究報告, Vol. SP2005, No. 20, pp. 1-6, June 2005.
• Arnar Jensson, Edward Whittaker, Koji Iwano, Sadaoki Furui. Language model adaptation for ASR using machine-translated data, 電子情報通信学会 技術研究報告, Vol. SP2005, No. 23, pp. 19-23, June 2005.
• 赤川達也, Koji Iwano, Sadaoki Furui. HMMを用いた話し言葉音声合成の実現に向けての検討, 電子情報通信学会 技術研究報告, Vol. SP2005, No. 16, pp. 25-30, May 2005.
• Ryuta Nakagawa, 小林 唯, 小林 隆二, Koichi Shinoda, Sadaoki Furui. 音声と手書き文字の同時入力インターフェース, 情報処理学会 音声言語情報処理研究会, 情報処理学会 研究報告, Vol. 2005, No. SLP-56, pp. 29-34, May 2005.
• Masanobu Nakamura, Koji Iwano, SADAOKI FURUI. マハラノビス距離を用いた日本語話し言葉音声の音響的特徴の分析, 日本音響学会2005年春季研究発表会, 日本音響学会2005年春季講演論文集, 日本音響学会, No. 2-1-4, pp. 231-232, Mar. 2005.
• Arnar Jensson, Edward Whittaker, Sadaoki Furui. Improving a language model using machine translated data, 日本音響学会2005年春季講演論文集, No. 1-5-26, pp. 51-52, Mar. 2005.
• Paul Dixon, Sadaoki Furui, Martin Russell. Speaker identification using products of experts, 日本音響学会2005年春季研究発表会, 日本音響学会2005年春季講演論文集, 日本音響学会, No. 1-5-5, pp. 9-10, Mar. 2005.
• 新中庸介, Koji Iwano, SADAOKI FURUI. 講演音声のインデキシングを目的としたセグメンテーション手法の検討, 日本音響学会2005年春季研究発表会, 日本音響学会2005年春季講演論文集, 日本音響学会, No. 1-5-4, pp. 7-8, Mar. 2005.
• 小林隆二, Koichi Shinoda, SADAOKI FURUI. 弁別素性のグラフィカルモデリングによる音声認識, 音声音響学会2005年春季研究発表会, 日本音響学会2005年春季講演論文集, 音声音響学会, No. 1-5-21, pp. 41-42, Mar. 2005.
• Javier Latorre, Koji Iwano, Sadaoki Furui. Addition of new languages to a polyglot HMM-based synthesizer, 日本音響学会2005年春季研究発表会, 日本音響学会2005年春季講演論文集, 日本音響学会, No. 1-1-22, pp. 197-198, Mar. 2005.
• 広畑誠, 新中庸介, Koji Iwano, SADAOKI FURUI. 客観尺度を用いた音声自動要約手法の評価, 音声音響学会2005年春季研究発表会, 音声音響学会2005年春季講演論文集, 音声音響学会, No. 1-5-2, pp. 3-4, Mar. 2005.
• 田村哲嗣, Koji Iwano, SADAOKI FURUI. 実環境を考慮したマルチモーダル音声認識のためのストリーム重み最適化手法, 情報処理学会 研究報告, Vol. 2005, No. SLP-55, pp. 29-34, Feb. 2005.

Other Publication

• SADAOKI FURUI. 大規模知識資源の体系化と活用基盤構築, 情報処理, Vol. 46, No. 5, pp. 488-496, May 2005.

[ Save as BibTeX ]    [ Paper, Presentations, Books, Others, Degrees: Save as CSV ]    [ Patents: Save as CSV ]