Published 'Speech synthesis based on large pretrained models' in Journal of Acoustical Society of Japan, Vol. 81, No. 10, Oct. 2025.
Published 'Empathetic dialogue speech synthesis: Speech synthesis towards more expressive spoken dialogue systems' in Journal of Acoustical Society of Japan, Vol. 80, No. 12, Dec. 2024.
Contributed to multiple research papers including 'Language-queried target speech extraction using para-linguistic and non-linguistic prompts', 'JVNV: A corpus of Japanese emotional speech with verbal content and nonverbal expressions', etc.
Received 2021 IEICE Journal Paper Award.
Presented a poster 'Perceptual-similarity-aware deep speaker representation learning for multi-speaker generative modeling' at ICASSP2022.
Research Experience
Lecturer (Senior Assistant Professor) at System #1 Lab, University of Tokyo; Cross-Appointment Fellow at National Institute of Advanced Industrial Science and Technology, Artificial Intelligence Research Center, Intelligent Media Processing Research Team.
Education
No specific educational background information provided.
Background
Research interests: speech synthesis, voice conversion, machine learning, machine intelligence, and so on. Currently a Lecturer (Senior Assistant Professor) in System #1 Lab at the University of Tokyo and also working as a Cross-Appointment Fellow at National Institute of Advanced Industrial Science and Technology, Artificial Intelligence Research Center, Intelligent Media Processing Research Team.