Academic Activities
Professor Daisuke Kawahara at Waseda University, Japan (2025 - Present)
Professor Kazuhiro Nakadai at Tokyo Institute of Technology, Japan (2024 - 2025)
Associate Professor Shinji Watanabe at CMU, USA (2021 – 2025)
OWSM: Large-scale Multilingual Speech Foundation Model (🏆ISCA Best Student Paper Award 2025🏆️)
DPHuBERT: Joint Distillation and Pruning of Self-Supervised Speech Models
Associate Professor Ryu Takeda at Osaka University, Japan (2021 – 2023)
Integration of Automatic Speech Recognition and Speech Enhancement based on Evidence Model
Professor Hirofumi Nakajima at Kogakuin University, Japan (2021 - 2022)
Online Adaptation of Fourier-series Acoustic Transfer Function to Improve Sound Source Localization and Separation
Supervised as Team Leader:
Master's student, University of Tokyo, Japan (2025.7 – Present)
Doctoral student, Toyohashi University of Technology, Japan (2025.6 – Present)
Prospective master's student, Waseda University, Japan (2025.6 – Present)
Doctoral student, Nagoya University, Japan (2025.5 – Present)
Supervised as Mentor:
Master's student, Tokyo Institute of Technology, Japan (2024.8 – 2024.11)
Undergraduate student, The University of British Columbia, Canada (2024.5 – 2024.12)
Master's student, Tokyo Institute of Technology, Japan (2022.12 – 2023.6)
Improving Noise Robustness of Automatic Speech Recognition based on a Parallel Adapter Model with Near-Identity Initialization (🏆JSAI Incentive Award🏆)
Doctoral student, Tokyo Institute of Technology, Japan (2021.12 – 2022.8)
Keio University, Department of System Design Engineering, Faculty of Science and Technology, Advanced System Design Engineering, Jun. 27th, 2024.
Keio University, School of Integrated Design Engineering, Graduate School of Science and Technology, System Design Engineering Exercise (TA), 2009-2010.
INTERSPEECH 2025: Decoding algorithm
RO-MAN 2023: Linguistic Communication and Dialogue
Journal: TASLP, Speech Communication, IEEE Access, TECS, Signal, Image and Video Processing, IEICE
Conference: ICASSP, INTERSPEECH, ASRU, SLT, IJCNN, ACL, RO-MAN, IROS