Koichi Shinoda


Koichi Shinoda


speech recognitionvideo searchpattern recognition


Koichi Shinoda received the B.S. and M.S. degrees from the University of Tokyo in 1987 and 1989, respectively, both in physics, and the D. Eng. Degree in computer science from Tokyo Institute of Technology, Japan, in 2001. In 1989, he joined NEC Corporation. From 1997 to 1998, he was a Visiting Scholar with Bell Labs, Lucent Technologies. From 2001, he was an Associate Professor with the University of Tokyo, Japan. He is currently a Professor with the Tokyo Institute of Technology. His research interests include speech recognition, video search, and pattern recognition.

Expectations for WRHI

Communication with researchers world-wide to expand our research


S. Biswas, J. Rohdin, K. Shinoda, “Autonomous Selection of i-Vectors for PLDA Modelling in Speaker Verification”, Elsevier Speech Communication, vol. 72, pp. 32-46, May 8, 2015.


N. Inoue, K. Shinoda, “Fast Coding of Feature Vectors using Neighbor-To-Neighbor Search”, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 38, no. 6, pp. 1170-1184, Sep. 23, 2015.


J. Rohdin, S. Biswas, K. Shinoda, “Robust Discriminative Training Against Data Insufficiency in PLDA-Based Speaker Verification”, Elsevier Computer Speech and Language, vol. 35, pp. 32-57, Jun. 20, 2015.


R. Price, K. Iso, K. Shinoda, “Wise Teachers Train Better DNN Acoustic Models”, EURASIP Journal on Audio Speech and Music Processing, 10, pp. 1-19, Apr. 12, 2016.


T. Kerola, N. Inoue, K. Shinoda, “Cross-View Human Action Recognition from Depth Maps Using Spectral Graph Sequences”, Elsevier Journal of Computer Vision and Image Understanding (CVIU), vol. 154, pp. 108-126, Jan. 1, 2017.