List of Publications & Open Source Activities
(October 2021) Controllable and Interpretable Singing Voice Decomposition via Assem-VC
(June 2021) Sharp Edge Recovery via SE(3)-Equivariant Network
- Presented at 2nd SHApe Recovery from Partial textured 3D scans at CVPR 2021
- 2nd place at SHAPR 2021 Challenge track 3
(April 2021) NU-Wave: A Diffusion Probabilistic Model for Neural Audio Upsampling
(April 2021) Assem-VC: Realistic Voice Conversion by Assembling Modern Speech Synthesis Techniques
(December 2020) DS4C Patient Policy Province Dataset: A Comprehensive COVID-19 Dataset for Causal and Epidemiological Analysis
- Accepted to Causal Discovery and Causality-Inspired Machine Learning Workshop at NeurIPS 2020
- paper link
(September 2020) 3D Room Layout Estimation Beyond the Manhattan World Assumption
- Presented at Holistic Scene Structures for 3D Vision at ECCV 2020
- 3rd place at Holistic 3D Vision Challenge track 1
(May 2020) Cotatron: Transcription-Guided Speech Encoder for Any-to-Many Voice Conversion without Parallel Data
(December 2021) HifiFace
(August 2021) UnivNet
(July 2021) WaveGrad2
(October 2020) FaceShifter
(June 2020) KoTDG
- Korean Text Data Generator for OCR tasks.
(March 2020) Data-Science-for-COVID-19
- COVID-19 Korea Dataset with patient routes and visualizer
- Co-led the collaboration project.
- News coverage: Link 1 Link 2
(January 2020) Reformer-pytorch
- Implementation of Reformer: The Efficient Transformer arXiv:2001.04451 in pytorch.
(October 2019) MelGAN
(August 2019) MelNet
- Implementation of MelNet: A Generative Model for Audio in the Frequency Domain arXiv:1906.01083.
- Work done with Deepest AI (SNU Deep Learning Society).
(April 2019) RandWireNN
- Implementation of Exploring Randomly Wired Neural Networks for Image Recognition arXiv:1904.01569.
(March 2019) VoiceFilter
- First successful open-source implementation of Google’s VoiceFilter arXiv:1810.04826.
(August 2018 – August 2020) Contribution to TensorFlow, PyTorch, Flashlight
- Made numerous contribution to the most popular deep learning frameworks, primarily by Isaac Lee (former CUDA Team leader). His name was proudly mentioned in the list of contributors at TensorFlow release note: Link