Kang-wook Kim

Hello, I am currently an undergraduate student majoring in Electrical and Computer Engineering at Seoul National University. At present, I am an intern at the Laboratory for Imaging Science and Technology (LIST), conducting research on bio imaging using deep learning.

My past experiences include a research internship at Supertone Inc. focusing on voice recognition, and a senior research scientist role at MINDsLab Inc., where I specialized in speech synthesis.

I am eager to pursue a Ph.D. degree abroad.

Email  /  CV  /  Google Scholar  /  Semantic Scholar  /  Twitter  /  Github  /  Linkedin

profile photo
Research

My research focus is on speech synthesis and deep learning, with a particular emphasis on analyzing and manipulating speech. Some of my notable papers are highlighted.

clean-usnob FS-NCSR: Increasing Diversity of the Super-Resolution Space via Frequency Separation and Noise-Conditioned Normalizing Flow
Ki-Ung Song*, Dongseok Shim*, Kang-wook Kim*, Jae-young Lee, Younggeun Kim
NTIRE CVPRW, 2022
arXiv

2nd place on the NTIRE Learning Super-Resolution Space Challenge 4X track and 1st place on the 8X track.

clean-usnob Talking Face Generation with Multilingual TTS
Hyoung-Kyu Song*, Sang Hoon Woo*, Junhyeok Lee, Seungmin Yang, Hyunjae Cho, Youseong Lee, Dongho Choi, Kang-wook Kim
CVPR Demo Track (Round 1), 2022
arXiv / Demo

clean-usnob Assem-VC: Realistic Voice Conversion by Assembling Modern Speech Synthesis Techniques
Kang-wook Kim, Seung-won Park, Junhyeok Lee, Myun-chul Joe
To appear in Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2022
project page / arXiv / github

clean-usnob Controllable and Interpretable Singing Voice Decomposition via Assem-VC
Kang-wook Kim, Junhyeok Lee
NeurIPS Workshop on ML for Creativity and Design, 2021   (Oral Presentation [top 6.2%])
project page / arXiv / github / bibtex

We propose a controllable singing decomposition system that encodes time-aligned linguistic content, pitch, and source speaker identity via Assem-VC.