Koichi Shinoda

Professor

Research Interest:

Statistical pattern processing, Speech recognition, Video understanding, and Human-computer interaction (See Research for details).

Profile

Koichi Shinoda received the B.S. and M.S. degrees from the University of Tokyo, Tokyo, Japan, in 1987 and 1989, respectively, both in physics, and the D. Eng. Degree in computer science from the Tokyo Institute of Technology, Japan, in 2001. In 1989, he joined NEC Corporation, Japan, where he was involved in research on automatic speech recognition. From 1997 to 1998, he was a Visiting Scholar with Bell Labs, Lucent Technologies, Murray Hill, NJ. From June 2001 to September 2001, he was a Principal Researcher with Multimedia Research Laboratories, NEC Corporation. From October 2001 to March 2002, he was an Associate Professor at the University of Tokyo, Japan. He is currently a Professor at the Tokyo Institute of Technology. His research interests include speech recognition, video information retrieval, statistical pattern recognition, and human interfaces. He received the Awaya Prize from the Acoustic Society of Japan in 1997 and the Excellent Paper Award from the IEICE in 1998. He was Publicity Chair in INTERSPEECH2010, Video Program Co-Chair in ACM Multimedia 2012. Dr. Shinoda is a senior member of IEEE, IEICE. He is a member of ACM, IPSJ, JSAI, and ASJ. He was a subject editor of Speech Communication from 2013 to 2015. He is currently an associate editor of Computer Speech and Language, Elsevier.

Publications

(Not updated. See publications for recent info).

Papers

S. Sagayama, K. Shinoda, M. Nakai and H. Shimodaira ``Analytic Methods for Acoustic Model Adaptation: A Review,'' in Proc. Isca ITR-Workshop2001, pp. 67-76, Sophia-Antipolis, 2001.
T. Emori and K. Shinoda, ``Rapid Vocal Tract Length Normalization using Maximum Likelihood Estimation,'' in Proc. EuroSpeech2001, pp. 1649-1652, Aalborg, 2001.
K. Shinoda and C.-H. Lee, ``A structural Bayes approach to speaker adaptation'', IEEE Trans. Speech Audio Processing, vol. 9, no. 3, pp. 276-287, 2001.
K. Shinoda and T. Watanabe, ``MDL-based context-dependent subword modeling for speech recognition,'' J. Acoust. Soc. Jpn.(E), vol. 21, no. 2, pp.79-86, 2000.
K. Shinoda and C.-H. Lee, ``Unsupervised adaptation using structural Bayes approach,'' in Proc. ICASSP-98, Seattle, pp. II 793-796, 1998.
K. Shinoda and C.-H. Lee, ``Structural MAP speaker adaptation using hierarchical priors,'' Proc. IEEE Workshop on Speech Recognition and Understanding, Santa Barbara, pp. 381-387, 1997.
K. Shinoda and T. Watanabe, ``Acoustic modeling based on the MDL criterion for speech recognition,'' in Proc. EuroSpeech-97, Rhodes, vol. 1, pp. 99-102, 1997.
K. Takagi, K. Shinoda, H. Hattori, and T. Watanabe, ``Unsupervised and incremental speaker adaptation under adverse environmental conditions,'' in Proc. ICSLP-96, Atlanta, pp. 2079-2082, 1996.
K. Shinoda and T. Watanabe, ``Speaker adaptation with autonomous model complexity control by MDL principle,'' in Proc. ICASSP-96, Atlanta, pp.717-720, 1996.
K. Shinoda and T. Watanabe, ``Speaker adaptation with autonomous control using tree structure,'' in Proc. EuroSpeech-95, Madrid, pp. 1143-1146, 1995.
T. Watanabe, K. Shinoda, K. Takagi, and K. Iso, ``High speed speech recognition using tree-structured probability density function,'' in Proc. ICASSP-95, Detroit, pp. 556-559, 1995.
K. Shinoda and T. Watanabe, ``Unsupervised speaker adaptation for speech recognition using demi-syllable HMM,'' in Proc. ICSLP-94, Yokohama, pp. 435-438, 1994.
T. Watanabe, K. Shinoda, K. Takagi, and E. Yamada, ``Speech recognition using tree-structured probability density function,'' in Proc. ICSLP-94, Yokohama, pp. 223-226, 1994.
K. Shinoda, K. Iso, and T. Watanabe, ``Speaker Adaptation for Demi-Syllable-Based Continuous-Density HMM,'' in Proc. ICASSP-91, Toronto, pp. 857-860, 1991.
K. Shinoda, K. Iso, and T. Watanabe, ``Speaker adaptation for demi-syllable based speech recognition using continuous HMM,'' in Proc. of ICSLP-90, Kobe, pp. 261-264, 1990.

Patents

US5274737 ``Reference pattern adapting device trainable by a small number of training patterns''
EU0469577 ``Reference pattern adapting device trainable by a small number of training patterns''
US5956676 ``Pattern adapting apparatus using minimum description length criterion in pattern recognition processing and speech recognition system''
US5960396 ``Standard pattern production system employing information criterion''
US6173076B1 ``Speech Recognition pattern adaptation system using tree scheme''

Dear Prospective Students Abroad,

I appreciate your interest in Shinoda Lab, Institute of Science Tokyo.

We always welcome students who want to study speech and video signal processing, statistical pattern recognition, and deep learning. Since our area is quite interdisciplinary, our lab comprises students with various backgrounds, such as computer science, electric engineering, applied physics, and physiology. We also emphasize diversity. We welcome students from all over the world. Our lectures, seminars, and research discussions are in English. You do not have to learn Japanese for your research (of course, you have to learn the minimum "survival" Japanese for your daily life in Japan).

If you would like to apply for our lab, please send the following to me by e-mail.

CV
Scanned copies of academic transcripts, preferably, with your GPA and your rank in your class.
Scanned copy of your official English score sheet.
Research plan you would like to follow when you come to our lab. It should be concrete and original.

Please write them in English. No other information is needed. For example, you do not have to show how much you like Japan or Japanese culture, how much your Japanese is good, how much you have done social activities at your university, or how eagerly you would like to study in our lab.

Contact

Department of Computer Science, School of Computing, Institute of Science Tokyo

2-12-1, Ookayama, Meguro-ku, Tokyo, 152-8552, Japan.

TEL/FAX: +81-3-5734-3480

E-mail: shinoda_at_c.titech.ac.jp

Page updated

Report abuse