Received the Research Fellowship for Young Scientists (DC1) from Japan Society for the Promotion of Science (JSPS), lasting from April 2021 to March 2024.
Co-organizer of the VoiceMOS Challenge series, Voice Conversion Challenge 2020, and Singing Voice Conversion Challenge 2023.
Honored with the Outstanding Graduate Student Award (学術奨励賞) of Nagoya University in 2023.
Received the 16th IEEE Signal Processing Society Japan Student Best Paper Award, the Best Paper Award at the 13th Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) in 2021, and the Best Student Paper Award at the 11th International Symposium on Chinese Spoken Language Processing (ISCSLP) in 2018.
Reviewer for several journals including IEEE SPL, IEEE/ACM TASLP, Speech Communication, etc.
Presented two papers at Interspeech 2025.
Gave a tutorial at Interspeech 2025 on the topic “Automatic Quality Assessment for Speech and Beyond”.
Published a journal in IEEE Journal of Selected Topics in Signal Processing.
Organized and participated in AudioMOS Challenge 2025 and Singing Voice Conversion Challenge 2025.
Gave an online invited talk at the Conversational AI Reading Group, MILA.
Research Experience
Student researcher at Google Japan from April 2023 to March 2024, supervised by Yuma Koizumi.
Research intern at FAIR (Fundamental AI Research), Meta, from May to September 2022, working on speech-to-speech translation, supervised by Peng-Jen Chen.
Research intern at Reality Labs Research (RL-R), Meta, from August 2021 to February 2022, working on binaural speech synthesis, supervised by Dejan Markovic.
Interned at NTT Communication Science Laboratories, NTT Corporation, from August 2019 to September 2019, supervised by Prof. Hirokazu Kameoka.
Research assistant at the Institute of Information Science in Academia Sinica, Taipei, Taiwan, from July 2017 to March 2019, advised by Prof. Hsin-Min Wang and Prof. Yu Tsao.
Education
Received B.S. in Computer Science and Information Engineering from National Taiwan University in 2018; M.S. and Ph.D. from the Graduate School of Informatics, Nagoya University in 2021 and 2024, respectively.
Background
Research interests: speech processing, with a main focus on speech quality assessment, voice conversion, and speech synthesis. Related applications include speaking-aid and accent conversion.
Miscellany
Spends most of his free time golfing since 2023, with a best score of 86 (regular tee). Also danced for over 10 years, though not as frequently now.