Short Academic Profile
Kenichi Fujita, Ph.D. (Engineering)
Research Scientist specializing in Zero-shot Text-to-Speech (TTS), Speaker Modeling, and High-Fidelity Speech Synthesis.
Currently working at NTT on advanced neural speech generation systems for real-world applications.
My research focuses on robust and controllable speech synthesis, speaker adaptation, and practical deployment of TTS technologies.
Research Interests
Zero-shot Text-to-Speech
Speaker Representation Learning
High-Fidelity Neural Speech Synthesis
Robust Speech Generation for Real-world Environments
Current Position
NTT Corporation — Research Scientist (2020–Present)
Research and development of neural speech synthesis systems, focusing on high-quality, speaker-adaptive TTS models for practical applications.
Education
Ph.D. in Engineering, University of Tsukuba (2024–2025)
Dissertation: Study on High Speaker Fidelity Zero-Shot Text-to-Speech and Its Real-World Applications
M.S., The University of Tokyo (2020)
Research on autonomous underwater vehicles and multi-AUV positioning systems.
B.S., The University of Tokyo (2017)
Research on physical reservoir computing using dynamical body systems.
Awards
IEEE ICASSP 2023 SASB Workshop Best Paper Award
IIAE ICISIP 2017 Best Presentation Award
1st Prize, Underwater Robots Competition OTO’18