About
I am 3nd-year PhD student at Spoken Language Processing Laboratory (Kitaoka Lab), Toyohashi Unversity of Technology, under the supervision of Prof. Norihide Kitaoka.
I am interested in speech recognition and natural language processing.
I’m currently looking for a job after graduation.
Education
- April 2024 - present
PhD of Engineering- Research Topic: End-to-end speech recognition
- Supervisor: Prof. Norihide Kitaoka
- April 2022 - March 2024
Master of Engineering- Research Topic: End-to-end speech recognition
- Supervisor: Prof. Norihide Kitaoka
- April 2017 - March 2022
Bachelor of Engineering- Research Topic: Statistical machine learning, Bayesian inference
- Supervisor: Prof. Kazuho Watanabe
Research and Work Experiences
- Jun 2025 - present
SB intuitions- Research internship
- Worked on Speech processing, Speech Foundation Models
- Mentor: Dr. Yusuke Fujita, Dr. Yui Sudo
- July 2025 - september 2025
NTT Communication Science Laboratories- Visiting researcher
- Worked on end-to-end speech recognition and domain adaptaion
- Mentor: Dr. Atsunori Ogawa
- October 2024 - May 2025
Kotoba Technologies- Research internship
- Worked on speech processing
- Mentor: Dr. Jungo Kasai, Dr. Noriyuki Kojima
- October 2023 - May 2025
Fusic Co.- Research Engineer internship
- Worked on speech processing
- Mentor: Kai Washizaki, Beomseok Han
- March 2022 - March 2026
NTT Communication Science Laboratories- Collaborative research
- Worked on end-to-end speech recognition and domain adaptaion
- Mentor: Dr. Atsunori Ogawa
- April 2021 - March 2024
Garage Coffee Company- Part-time barista
- Worked on Coffee and Latte ☕️
Grants
- TUT-DC Fellowship (JST-SPRING)
- April 2024 - March 2027
- Living expenses: 2,300,000 JPY/year
- Research funds: 400,000 JPY/year
- Repayment Exemption for Graduate Students with Excellent Achievements from JASSO
- April 2022 – March 2024
- Half repayment waiver for outstanding performance
Activities/Talks/Others
- ICASSP 2025 Paper Reading
- paper:Automatic Parkinson’s disease detection from speech: Layer selection vs adaptation of foundation models
- ICASSP 2024 Paper Reading
- paper: Stateful Conformer with Cache-based Inference for Streaming Automatic Speech Recognition (NVIDIA)
- Acoustical Society of Japan, ASJ 2025
- Outstanding Student Presentation Award
- Interspeech 2025 Speech Accessibility Project Challenge
- 3rd Place🥉
- Hack Aichi+2023
- Excellence Award🥈
- Company Prize: Higashiyama Corporation