Koichi Shinoda

Hilman Ferdinandus Pardede, Koji Iwano, Koichi Shinoda: Feature normalization based on non-extensive statistics for speech recognition. Speech Communication 55(5): 587-599 (2013)

Koichi Shinoda, Nakamasa Inoue: Reusing Speech Techniques for Video Semantic Indexing [Applications Corner]. IEEE Signal Process. Mag. 30(2): 118-122 (2013)

Muhammad Rasyid Aqmar, Koichi Shinoda, Sadaoki Furui: Robust Gait-Based Person Identification against Walking Speed Variations. IEICE Transactions 95-D(2): 668-676 (2012)

Takafumi Koshinaka, Kentaro Nagatomo, Koichi Shinoda: Online Speaker Clustering Using Incremental Learning of an Ergodic Hidden Markov Model. IEICE Transactions 95-D(10): 2469-2478 (2012)

Hiroko Murakami, Koichi Shinoda, Sadaoki Furui: Active Learning Using Phone-Error Distribution for Speech Modeling. IEICE Transactions 95-D(10): 2486-2494 (2012)

Nakamasa Inoue, Koichi Shinoda: A Fast and Accurate Video Semantic-Indexing System Using Fast MAP Adaptation and GMM Supervectors. IEEE Transactions on Multimedia 14(4): 1196-1205 (2012)

Nakamasa Inoue, Koichi Shinoda: q-Gaussian Mixture Models Based on Non-extensive Statistics for Image and Video Semantic Indexing. ACCV (2) 2012: 499-510

Yusuke Kamishima, Nakamasa Inoue, Koichi Shinoda, Shunsuke Sato: Multimedia event detection using GMM supervectors and SVMS. ICIP 2012: 3089-3092

Hilman Ferdinandus Pardede, Koichi Shinoda, Koji Iwano: Q-Gaussian based spectral subtraction for robust speech recognition. INTERSPEECH 2012

Ryo Yokoyama, Yu Nasu, Koichi Shinoda, Koji Iwano: Overlapped Speech Detection in Meeting Using Cross-Channel Spectral Subtraction and Spectrum Similarity. INTERSPEECH 2012

Yuzo Hamanaka, Koichi Shinoda, Takuya Tsutaoka, Sadaoki Furui, Tadashi Emori, Takafumi Koshinaka: Committee-Based Active Learning for Speech Recognition. IEICE Transactions 94-D(10): 2015-2023 (2011)

Koichi Shinoda, Yasushi Watanabe, Kenji Iwata, Yuan Liang, Ryuta Nakagawa, Sadaoki Furui: Semi-synchronous speech and pen input for mobile user interfaces. Speech Communication 53(3): 283-291 (2011)

Hiroko Murakami, Koichi Shinoda, Sadaoki Furui: Designing text corpus using phone-error distribution for acoustic modeling. ASRU 2011: 191-195

Yu Nasu, Koichi Shinoda, Sadaoki Furui: Cross-Channel Spectral Subtraction for meeting speech recognition. ICASSP 2011: 4812-4815

Marc Ferras, Koichi Shinoda, Sadaoki Furui: Structural MAP adaptation in GMM-supervector based speaker recognition. ICASSP 2011: 5432-5435

Hilman Ferdinandus Pardede, Koichi Shinoda: Generalized-Log Spectral Mean Normalization for Speech Recognition. INTERSPEECH 2011: 1645-1648

Marc Ferras, Koichi Shinoda, Sadaoki Furui: Structural Joint Factor Analysis for Speaker Recognition. INTERSPEECH 2011: 2373-2376

Sangeeta Biswas, Marc Ferras, Koichi Shinoda, Sadaoki Furui: Acoustic Forest for SMAP-Based Speaker Verification. INTERSPEECH 2011: 2377-2380

Nakamasa Inoue, Koichi Shinoda: A fast MAP adaptation technique for gmm-supervector-based video semantic indexing systems. ACM Multimedia 2011: 1357-1360

Koichi Shinoda: Acoustic Model Adaptation for Speech Recognition. IEICE Transactions 93-D(9): 2348-2362 (2010)

Yuzo Hamanaka, Koichi Shinoda, Sadaoki Furui, Tadashi Emori, Takafumi Koshinaka: Speech modeling based on committee-based active learning. ICASSP 2010: 4350-4353

Muhammad Rasyid Aqmar, Koichi Shinoda, Sadaoki Furui: Robust Gait Recognition Against Speed Variation. ICPR 2010: 2190-2193

Nakamasa Inoue, Tatsuhiko Saito, Koichi Shinoda, Sadaoki Furui: High-Level Feature Extraction Using SIFT GMMs and Audio Models. ICPR 2010: 3220-3223

Hitoshi Yamamoto, Ken Hanazawa, Kiyokazu Miki, Koichi Shinoda: Dynamic language model adaptation using keyword category classification. INTERSPEECH 2010: 2426-2429

Nakamasa Inoue, Toshiya Wada, Yusuke Kamishima, Koichi Shinoda, Ilseo Kim, Byungki Byun, Chin-Hui Lee: TT+GT at TRECVID 2010 Workshop. TRECVID 2010

Takafumi Koshinaka, Kentaro Nagatomo, Koichi Shinoda: Online speaker clustering using incremental learning of an ergodic hidden Markov model. ICASSP 2009: 4093-4096

Hsin-Lung Hsieh, Jen-Tzung Chien, Koichi Shinoda, Sadaoki Furui: Independent component analysis for noisy speech recognition. ICASSP 2009: 4369-4372

Koichi Shinoda, Hiroko Murakami, Sadaoki Furui: Speaker adaptation based on two-step active learning. INTERSPEECH 2009: 576-579

Agnieszka Betkowska Cavalcante, Koichi Shinoda, Sadaoki Furui: Robust Speech Recognition in the Car Environment. LTC 2009: 24-34

Shutaro Tanji, Koichi Shinoda, Sadaoki Furui, Antonio Ortega: Improvement of eigenvoice-based speaker adaptation by parameter space clustering. INTERSPEECH 2008: 1229-1232

Kenji Iwata, Koichi Shinoda, Sadaoki Furui: Robust spoken term detection using combination of phone-based and word-based recognition. INTERSPEECH 2008: 2195-2198

Yasushi Watanabe, Koichi Shinoda, Sadaoki Furui: Time-lag adaptation for semi-synchronous speech and pen input. INTERSPEECH 2008: 2675-2678

Koichi Shinoda, Kazuki Ishihara, Sadaoki Furui, Takahiro Mochizuki: Automatic Score Scene Detection for Baseball Video. LKR 2008: 226-240

Koji Yamasaki, Koichi Shinoda, Sadaoki Furui: Automatically estimating number of scenes for rushes summarization. TVS 2008: 129-133

Shanshan Hao, Yusuke Yoshizawa, Koji Yamasaki, Koichi Shinoda, Sadaoki Furui: Tokyo Tech at TRECVID 2008. TRECVID 2008

Agnieszka Betkowska, Koichi Shinoda, Sadaoki Furui: Robust Speech Recognition Using Factorial HMMs for Home Environments. EURASIP J. Adv. Sig. Proc. 2007 (2007)

Ryoichi Ando, Koichi Shinoda, Sadaoki Furui, Takahiro Mochizuki: A robust scene recognition system for baseball broadcast using data-driven approach. CIVR 2007: 186-193

Jen-Tzung Chien, Koichi Shinoda, Sadaoki Furui: Predictive minimum Bayes risk classification for robust speech recognition. INTERSPEECH 2007: 1062-1065

Tadashi Emori, Yoshifumi Onishi, Koichi Shinoda: Automatic estimation of scaling factors among probabilistic models in speech recognition. INTERSPEECH 2007: 1453-1456

Hiroki Yamazaki, Koji Iwano, Koichi Shinoda, Sadaoki Furui, Haruo Yokota: Dynamic language model adaptation using presentation slides for lecture speech recognition. INTERSPEECH 2007: 2349-2352

Taichi Nakamura, Koichi Shinoda, Sadaoki Furui: TokyoTech's TRECVID2007 Notebook. TRECVID 2007

Nguyen Huu Bach, Koichi Shinoda, Sadaoki Furui: Robust Scene Extraction Using Multi-Stream HMMs for Baseball Broadcast. IEICE Transactions 89-D(9): 2553-2561 (2006)

Ryoichi Ando, Koichi Shinoda, Sadaoki Furui, Takahiro Mochizuki: Robust scene recognition using language models for scene contexts. Multimedia Information Retrieval 2006: 99-106

Nguyen Huu Bach, Koichi Shinoda, Sadaoki Furui: Robust highlight extraction using multi-stream hidden Markov models for baseball video. ICIP (3) 2005: 173-176

Tadashi Emori, Koichi Shinoda: Vocal tract length normalization using rapid maximum-likelihood estimation for speech recognition. Systems and Computers in Japan 33(5): 30-40 (2002)

Koichi Shinoda, Ken-ichi Iso: Efficient reduction of Gaussian components using MDL criterion for HMM-based speech recognition. ICASSP 2002: 869-872

Koichi Shinoda, Chin-Hui Lee: A structural Bayes approach to speaker adaptation. IEEE Transactions on Speech and Audio Processing 9(3): 276-287 (2001)

Tadashi Emori, Koichi Shinoda: Rapid vocal tract length normalization using maximum likelihood estimation. INTERSPEECH 2001: 1649-1652

Koichi Shinoda, Mieko Yamada: A family of Hadamard matrices of dihedral group type. Discrete Applied Mathematics 102(1-2): 141-150 (2000)

Koichi Shinoda, Takao Watanabe: Acoustic modeling based on the MDL principle for speech recognition. EUROSPEECH 1997

Keizaburo Takagi, Koichi Shinoda, Hiroaki Hattori, Takao Watanabe: Unsupervised and incremental speaker adaptation under adverse environmental conditions. ICSLP 1996

Koichi Shinoda, Takao Watanabe: Speaker adaptation with autonomous control using tree structure. EUROSPEECH 1995

Koichi Shinoda, Takao Watanabe: Unsupervised speaker adaptation for speech recognition using demi-syllable HMM. ICSLP 1994

Takao Watanabe, Koichi Shinoda, Keizaburo Takagi, Eiko Yamada: Speech recognition using tree-structured probability density function. ICSLP 1994

Koichi Shinoda, Ken-ichi Iso, Takao Watanabe: Speaker adaptation for demi-syllable based speech recognition using continuous HMM. ICSLP 1990