Experience

Education

Combined M.S. & Ph.D. Mar. 2016 - Feb. 2021
Dept. of Electrical & Electronic Engineering, Yonsei University, South Korea
- Dissertation: Self-supervised Cross-modal Representation for Visual-Guided Speech Separation
- Advisor: Prof. Hong-Goo Kang


Barchelor's Degree. Mar. 2012 - Feb. 2016
Dept. of Electrical & Electronic Engineering, Yonsei University, South Korea
- Full Scholarship: The National Scholarship for Science and Engineering (KOSAF)


Experiences

Research Scientist Nov. 2020 - Present
Clova Speech, Naver Corporation, South Korea (Nov. 2020 - Dec. 2022)
Clova Speech, Naver Cloud Corporation, South Korea(Dec. 2022 - Present)
- Development of acoustic modeling for the open-vocabulary keyword spotting system
- Advanced research on speech preprocessing models including enhancement and separation
- Advanced research on the multi-modal learning and its applications

Deep Learning Instructor Oct. 2018 - Present
NVIDIA Corporation, USA
- Instruction of several deep learning courses using DLI program by NVIDIA Corporation

Internship Research Scientist Jul. 2018 - Dec. 2018
Clova, Naver Corporation, South Korea
- Collaborative research on speech separation and recognition modeling
- Advanced research on audio-visual signal processing and related paper works


Academic Activities

Reviewer
ICASSP, INTERSPEECH, MDPI, Speech Communications

Organizer
Spoofing-aware Speaker Verification (SASV) Challenge, 2022

Session Chair
INTERSPEECH, 2022


Honors and Awards

Best Paper Awards INTERSPEECH, ISCA. Sep., 2020
Paper: FaceFilter: Audio-visual Speech Separation using Still Images

Best Paper Finalist INTERSPEECH, ISCA. Sep., 2022
Paper: Learning Audio-Text Agreement for Open-vocabulary Keyword Spotting