Hi, I am a 2nd-year Ph.D. student at Graduate school of Information Science and Technology, the University of Tokyo, Japan. My CV is available [here].

My research has focused on spoken language processing including speech synthesis, speech representation learning, speech quality assessment, etc. I am particularly interested in building speech processing models leveraging a wide variety of existing data or foundation models. This enables the model to learn diverse expressions, languages, prosody, and speaker individuality, which can familiarize artificial voice user interfaces more.

Email (university): takaaki_saeki [at] ipc.i.u-tokyo.ac.jp
Email (personal): saefrospace [at] gmail.com
Address: Room #140, Engineering bldg. #6, 7-3-1 Hongo, Bunkyo-ku, Tokyo 113-8656, Japan


Awards & Honours

Grants & Scholarships


Miscellaneous Work