Tomohiro Nakatani
Scholar

Tomohiro Nakatani

Google Scholar ID: kfUs6UAAAAAJ
NTT Communication Science Laboratories
Statistical audio signal processingComputational auditory scene analysis
Citations & Impact
All-time
Citations
7,159
 
H-index
42
 
i10-index
125
 
Publications
20
 
Co-authors
48
list available
Contact
No contact links provided.
Resume (English only)
Academic Achievements
  • - 2020 AI2000 Most Influential Scholars Honorable Mention
  • - 2018 International Workshop on Acoustic Signal Enhancement (IWAENC) Best Paper Award
  • - 2017 Maejima Hisoka Award
  • - 2015 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) Best Paper Award Honarable Mention
  • - 2015 3rd CHiME Speech Separation and Recognition Challenge (CHiME3) Best Score
  • - 2014 REVERB Challenge Best Score
  • - 2012 Japan Audio Society Award
  • - 2011 1st CHiME Speech Separation and Recognition Challenge (CHiME1) Best Score
  • - 2011 Acoustical Society of Japan (ASJ) Technical Development Award
  • - 2005 the Institute of Electronics, Information and Communication Engineers (IEICE) Paper Awards
  • - 1997 the Japanese Society for Artificial Intelligence (JSAI) Conference Best Paper Award
Research Experience
  • - 2001 - Present: Senior Research Scientist (2001-2019) and Senior Distinguished Researcher (2019-Present), Communication Science Laboratories, NTT Corporation
  • - 2008 - 2018: Visiting Associate Professor, Nagoya University
  • - 2005 - 2006: Visiting Scholar, Georgia Institute of Technology
  • - 1999 - 2001: Technical staff member, Corporate Business Headquarters, NTT-east Corporation
  • - 1998 - 1999: Technical staff member, Multimedia Business Department, NTT Corporation
  • - 1991 - 1998: Researcher, Basic Research Laboratory, NTT Corporation
Education
  • - B.E., Department of Precision Engineering, Kyoto University, Japan, 1989. Thesis title: Parameter adaptation methods for a learning control system. Supervisor: Professor Yutaka Yamamoto
  • - M.E., Division of Applied System Science, Kyoto University, Japan, 1991. Thesis title: Composite neural networks. Supervisor: Professor Yutaka Yamamoto
  • - Ph.D., Department of Applied Analysis and Complex Dynamical Systems, Kyoto University, Japan, March 2002. Dissertation title: Computational auditory scene analysis based on residue-driven architecture and its application to mixed speech recognition. Supervisor: Professor Yutaka Yamamoto
Background
  • - Research Interests: Single and multi channel speech enhancement, dereverberation, denoising, and source separation with statistical signal processing approach, robust automatic speech recognition (ASR), integration of speech enhancement, ASR, and speech synthesis, computational auditory scene analysis, fundamental frequency estimation, voice activity detection, and spaker diarization
Miscellany
  • - Academic Activities: Distinguished Industry Speaker, IEEE Signal Processing Society (2025-2026), Member of Fellow Evaluating Committee, IEEE Signal Processing Society (2024-2025), Member of Spoken Language Processing Technical Committee, IEEE Signal Processing Society (2016-2021), Vice-Chair (2017-2018) and Chair (2019-2020) of Kansai Chapter, IEEE Signal Processing Society, etc.