1. Interests: Automatic speech recognition, non-native speech processing, and speech processing/AI in general
2. Skills: Python, PyTorch, Transformers, Fairseq, Kaldi, Docker, C, Java, Linux
3. Education
- B.A. in Linguistics / B.E. in Computer Science and Engineering at Seoul National University (2016-2021)
- M.A. in Linguistics at Seoul National University (2021-2023)
4. Experiences
- Exchange student at the University of Geneva (Spring of 2019)
- Intern at Speech Synthesis Team, Speech AI Lab, AI Center, NCSOFT (20.07-20.08, 20.11-21.02)
- Associate at AI Unit, Digital Innovation Division, Shinhan Bank (23.08 ~)
5. Publications
- Yeo, E. J.*, Ryu, H.*, Lee, J., Kim, S., & Chung, M. (2023). Comparison of L2 Korean Pronunciation Error Patterns from Five L1 Backgrounds by using Automatic Phonetic Transcription. Proc. ICPhS 2023. (https://arxiv.org/abs/2306.10821)
- Ryu, H., Kim, S., & Chung, M. (2023). A Joint Model for Pronunciation Assessment and Mispronunciation Detection and Diagnosis with Multi-task Learning. Proc. Interspeech 2023. (https://www.isca-speech.org/archive/pdfs/interspeech_2023/ryu23_interspeech.pdf)
6. Projects
- Japanese ASR (National Information Society Agency (NIA) 2022-2023)
- L2 Japanese phone recognition of Korean learners (National Information Society Agency (NIA) 2022-2023)
- L2 Korean pronunciation assessment of non-native learners of multinational backgrounds (National Information Society Agency (NIA) 2022-2023)