Yasunori Ohishi

Yasunori Ohishi

Senior Research Scientist, Supervisor

NTT Communication Science Laboratories

Biography

Yasunori Ohishi is a Senior Research Scientist, Supervisor, Group Leader of Computational Modeling Research Group in NTT Communication Science Laboratories. His research interests include acoustic signal processing, multimedia content analysis, and music information retrieval.

Interests
  • Acoustic signal processing
  • Multimedia content analysis
  • Music information retrieval
Education

  • PhD in Information Science, 2009

    Nagoya University

  • MSc in Information Science, 2006

    Nagoya University

  • BEng in Electrical and Electronic Engineering and Information Engineering, 2004

    Nagoya University

Recent Posts

A paper presented at EUSIPCO 2023
Please check out our EUSIPCO 2023 paper “First-shot anomaly sound detection for machine condition monitoring: A domain generalization baseline” by Noboru Harada, Daisuke Niizumi, Yasunori Ohishi, Daiki Takeuchi, Masahiro Yasuda.
Yasunori Ohishi
May 29, 2023 1 min read Anomaly detection
A paper presented at EUSIPCO 2023
NTT Communication Science Laboratories OPEN HOUSE 2023
The OPEN HOUSE will be held on June 1st (Thu.) and 2nd (Fri.) at NTT West QUINTBRIDGE in Osaka. The event website will also be lauched on 1 June at 12:00.
Yasunori Ohishi
May 27, 2023 1 min read Open House
Project
NTT Communication Science Laboratories OPEN HOUSE 2023
A paper presented at Interspeech 2023
We are pleased to announce that our paper “Masked Modeling Duo for Speech: Specializing General-Purpose Audio Representation to Speech using Denoising Distillation” by Daisuke Niizumi, Daiki Takeuchi, Yasunori Ohishi, Noboru Harada, and Kunio Kashino has been accepted to Interspeech 2023.
Yasunori Ohishi
May 22, 2023 1 min read General audio representation
A paper presented at Interspeech 2023
See all posts

Skills

Acoustic signal processing

Expert

Multimedia content analysis

Expert

Music information retrieval

Expert

Machine learning

Advanced

Bayesian statistics and modeling

Advanced

Python

Advanced

Recent Publications

Daisuke Niizumi, Daiki Takeuchi, Yasunori Ohishi, Noboru Harada, Masahiro Yasuda, Shunsuke Tsubaki, Keisuke Imoto (2024). M2D-CLAP: Masked Modeling Duo Meets CLAP for Learning General-purpose Audio-Language Representation. In Interspeech.

Cite Code arXiv

Shunsuke Tsubaki, Daisuke Niizumi, Daiki Takeuchi, Yasunori Ohishi, Noboru Harada, Keisuke Imoto (2024). Refining Knowledge Transfer on Audio-Image Temporal Agreement for Audio-Text Cross Retrieval. In EUSIPCO.

Cite arXiv

Daisuke Niizumi, Daiki Takeuchi, Yasunori Ohishi, Noboru Harada, Kunio Kashino (2024). Exploring Pre-trained General-purpose Audio Representations for Heart Murmur Detection. In EMBC.

Cite Code arXiv

See all publications

Projects

ConceptBeam
Target speech extraction based on “concept” or semantic information.
PDF arXiv
ConceptBeam
The Places Japanese audio caption corpus
Japanese spoken captions for the Places205 image dataset
PDF dataset
The Places Japanese audio caption corpus

Experience

 
 
 
 
 
Senior Research Scientist, Supervisor
NTT Communication Science Laboratories
Nov 2024 – Present Atsugi, Kanagawa, Japan
Group Leader of Computational Modeling Research Group, Media Information Laboratory in NTT Communication Science Laboratories.
 
 
 
 
 
Senior Manager
NTT Communication Science Laboratories
Nov 2022 – Oct 2024 Keihanna, Kyoto, Japan
Head of Human Resources in NTT Communication Science Laboratories.
 
 
 
 
 
Senior Research Scientist
NTT Communication Science Laboratories
Jun 2021 – Oct 2022 Atsugi, Kanagawa, Japan
Leading basic researches on acoustic signal processing, crossmodal semantic learning, audio captioning, and sound event localization and detection. Presented in major international conferences such as ICASSP, Interspeech, and DCASE.
 
 
 
 
 
Assistant Manager
NTT Communication Science Laboratories
Apr 2019 – May 2021 Atsugi, Kanagawa, Japan
Administrative and clerical supports for researchers and budget managements in Media Information Laboratory and Moriya Research Laboratory.
 
 
 
 
 
Senior Research Scientist
NTT Communication Science Laboratories
Oct 2017 – Mar 2019 Atsugi, Kanagawa, Japan
Leading basic researches on crossmodal semantic learning and multimedia event detection.
 
 
 
 
 
Deputy Manager
NTT Data
Oct 2014 – Sep 2017 Toyosu, Tokyo, Japan
Project leader for robust media search services, ‘MediaSearch+’
 
 
 
 
 
Research Scientist
NTT Communication Science Laboratories
Apr 2009 – Sep 2014 Atsugi, Kanagawa, Japan
Leading basic researches on singing voice information processing and sound event detection. Presented in major international conferences such as ICASSP and Interspeech.
 
 
 
 
 
PhD Student
Nagoya University
Apr 2006 – Mar 2009 Nagoya, Aichi, Japan
Research for analysis-synthesis model of singing voice that characterize varied singing behaviors and its practical applications.
 
 
 
 
 
MSc Student
Nagoya University
Apr 2004 – Mar 2006 Nagoya, Aichi, Japan
Research for discrimination between singing and speaking voices.
 
 
 
 
 
BEng Student
Nagoya University
Apr 2003 – Mar 2004 Nagoya, Aichi, Japan
Research for statistical analysis for the word hierarchy using an encyclopedic corpus.

Contact