Takuya Yoshioka's Research

Hello. I am a Research Scientist at NTT Communication Science Laboratories, working on speech technologies with the goal of making machines recognise human voices anywhere, especially in distant talking situations. I received a Ph.D. in Informatics from Kyoto University in 2010. I also conducted research at the University of Cambridge as a Visiting Scholar for one year in 2013. My current research is focused on deep neural networks for noise robust speech recognition. Technical areas which I specialise in include automatic speech recognition, speech enhancement, array processing, and machine learning.
Planned Publications/Presentations
  • Takuya Yoshioka, Shigeki Karita, and Tomohiro Nakatani, “Far-field speech recognition using CNN-DNN-HMM with convolution in time,” in Proceedings of the 2015 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2015), Apr. 2015.
  • Takuya Yoshioka and Mark J. F. Gales, “Environmentally robust ASR front-end for deep neural network acoustic models,” Computer Speech and Language, vol. 31, no. 1, pp. 65-86, May 2015.
Selected Publications
A complete list of my publications is available here.
Biography
Jul. 2014 - Present Research Scientist at NTT Communication Science Laboratories, Japan
Mar. 2013 - Mar. 2014 Visiting Scholar at the University of Cambridge, UK
Apr. 2006 - Jun. 2014 Researcher at NTT Communication Science Laboratories, Japan
Mar. 2010 Ph.D. in Informatics from Kyoto University, Japan
Mar. 2006 Master's in Informatics from Kyoto University, Japan
Jun. 2005 - Mar. 2006 Trainee at NTT Communication Science Laboratories, Japan
Aug. 2004 Intern at NTT Communication Science Laboratories, Japan
Mar. 2004 Bachelor's degree in Engineering from Kyoto University, Japan
Highlights
Academic Activities
  • Member of the Institute of Electrical and Electronics Engineers (IEEE)
  • Member of the International Speech Communication Association (ISCA)
  • Member of the Information Processing Society of Japan (IPSJ)
  • Publicity Co-Chair of The REVERB (REverberant Voice Enhancement and Recognition Benchmark) Workshop, 2014
  • Organising Committee Member of The REVERB Challenge, 2013-2014
  • Workshop Committee Member of 2007 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA 2007), 2007
Contact
Tel: +81 774 93 5326
E-mail: yoshioka.takuya@lab.ntt.co.jp
NTT Communication Science Laboratories
2-4, Hikari-dai, Seika-cho, Soraku-gun
Kyoto 619-0237, Japan