[Japanese] [English]

Takahiro Shinozaki

Professor

Department of Information and Communications Engineering
School of Engineering
Institute of Science Tokyo
4259-G2-2 Nagatsuta, Midori-ku, Yokohama
226-8501 Japan
Email:

Laboratory Home Page

Background

Department of Computer Science, Tokyo Institute of Technology, Japan, 2004 Ph.D.

Department of Computer Science, Tokyo Institute of Technology, Japan, 2001 M.E.

Department of Computer Science, Tokyo Institute of Technology, Japan, 1999 B.E.

Takahiro Shinozaki joined Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, Kanagawa, Japan in March 2013. Previously, he was an assistant professor in Graduate School of Advanced Integration Science, Chiba University, Chiba, Japan. He was an assistant professor in 2008-2011 and a fellowship researcher in 2007-2008 at Furui lab in Tokyo Institute of Technology, Tokyo, Japan. In 2006-2007, he was a research assistant professor at the Media Archiving Laboratory in Kyoto University, Kyoto, Japan. In 2004-2006, he was a research scholar at the Signal, Speech and Language Interpretation Laboratory in University of Washington, Seattle, Washington, USA. In 2005-2006, he was a visitor at International Computer Science Institute in Berkeley, California, USA.

Research

Takahiro Shinozaki's research interests include acoustic and language modeling for spontaneous speech recognition.

Publications

Software/Demos

FPGA implementation of a keyword spotter. MP4(11MB) (Reacts only to "midori" utterance)
Eye-input speech synthesis interface demonstration video MP4(5MB)
husky2 A fully pipeline based speech decoder.
Programs to run CV/Ag-EM algorithms
Scripts to run unsupervised CV adaptation
Scripts to train tied-state Gaussian mixture HMM using HTK English Japanese

Selected Projects

JSPS KAKENHI Grant-in-Aid for Challenging Exploratory Research,"Full Bayes model based unrestricted learning of speech recognition systems," (Principal Investigator, grant No. 17K20001) 2017.4-2019.3
Microsoft Academic-Industrial Collaboration Research Organization (IJARC) CORE12 Project, "Hardware speech sensor and its optimization based on evolutional methods," (Principal Investigator) 2016.
Third Frederick Jelinek Memorial Summer Workshop, "Building Speech Recognition System from Untranscribed Data," (Co-proposer) 2016.
JSPS KAKENHI Grant-in-Aid for Scientific Research (B), "Self-organization Learning of Speech Synthesis and Recognition System," (Principal Investigator, grant No. 26280055) 2014.4-2018.3
JSPS KAKENHI Grant-in-Aid for Challenging Exploratory Research, "Development of High Polymer Potential decoder using Graphical Model" (Principal Investigator, grant No.23650068) 2011.4-2014.3
Microsoft Academic-Industrial Collaboration Research Organization (IJARC) CORE5 Project, "Lightly supervised training based on CV framework using ML and discriminative criteria," (Principal Investigator) 2009.7-2010.6.
JSPS KAKENHI Grant-in-Aid for Young Scientists (B), "Research of Fast Noise Robust Speech Recognition Front End using Target Sounds Model Likelihood," (Principal Investigator, Grant No. 21700188) 2009.4-2011.3.
JSPS KAKENHI Grant-in-Aid for Young Scientists (B), "Research of Statistical Pattern Classifier Learning Algorithm using Cross-Validation Likelihood," (Principal Investigator, No. 19700167) 2007.4-2009.3.

Awards

IEICE-ISS Distinguished Achievement and Contributions Award (2018). IEICE
Yamashita SIG Research Award from Information Processing Society of Japan (IPSJ) in 2009.
The Awaya Prize from the Acoustical Society of Japan (ASJ) in 2008.
President of the United Nations Association of Japan Award, Kanagawa Biennial World Children's Art Exhibition in 1987.


	Robot, Oil, 2009 June.

[Laboratory top page]