About me

Career

Speech AI Researcher & Developer at Whispp (opens in a new tab) (Aug. 2022 ~ )
- Working on real-time whisper and vocal cord impaired speech to healthy speech conversion for those who lost their voices
- Main Research Topics:
  - Whisper & vocal cord impaired speech conversion
  - Robustness against different pathologies & breathing & background noise
  - Streaming voice conversion
  - Prosody preservation & prediction from atypical speech

University of Groningen, MSc. Voice Technology, Cum Laude, Valedictorian (Sep. 2021 ~ Aug. 2022)
- Courses: Speech Sounds, Programming, Machine Learning, Speech Recognition 1&2, Speech Synthesis 1&2
- Master thesis: "Dutch Dysarthric Speech Recognition: Applying Self-Supervised Learning to Overcome the Data Scacity Issue" (opens in a new tab)
- Some projects I have worked on
  - Rescoring low-resourced language ASR with N-gram lanugage model
  - E2E Catalan speech synthesis with transfer learning
  - Environment sounds classification with CNN-based moel
  - Parkinson's disease score prediction from speech
Keio University, B.A. Economics (Apr. 2017 ~ Mar. 2021)
- Relevant courses: Linear Algebra, Calculus, Statistics and Probability, Econometrics, Python Prigramming, Linguistics
Aalto University School of Business (Helsinki), Exchange Program (Sep. 2019 ~ May 2020)

Foundation of Deep Learning at University of Tokyo, Distinct Student (Apr. 2022 ~ Jun. 2022)