Jisoo Park

I am a Ph.D student in Computer Vision and Machine Learning (CVML) Lab at Chung-Ang University, advised by Junseok Kwon. I completed M.S in Artificial Intelligence and B.S in Computer Science and Engineering at the same institution.

My research interests include Audio-Visual speech processing (speech enhancement, separation, active speaker detection) and 3D Talking Head Generation.

My goal is to address diverse in the wild challenges and advance my research toward human-centered AI.

CV  /  Email  /  Github  /  LinkedIn

profile photo
News
  • I will be visiting University of Birmingham as a visiting researcher.
    Co-advised by Hyojin Park.
  • We have 1 paper accepted to ASRU 2025.
  • Internship at Korea Electronics Technology Institute (KETI).
  • We have 1 paper accepted to AAAI 2025.
  • We have 1 paper accepted to ECCV 2024 Workshop.
  • I visited University of Toronto as a visiting scholar.
Research
univoicelite Lightweight Wasserstein Audio-Visual Model for Unified Speech Enhancement and Separation
Jisoo Park*, Seonghak Lee*, Guisik Kim, Taewoo Kim, Junseok Kwonโ€ 
ASRU, 2025
pdf / code

IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), Honolulu, Hawaii, USA, 2025
ddml Deep Disentangled Metric Learning
Jinhee Park, Jisoo Park, Dakyeong Na, Junseok Kwonโ€ 
AAAI, 2025
pdf / code

The 39th Association for the Advancement of Artificial Intelligence (AAAI), Philadelphia, Pennsylvania, USA, 2025
iris Enhancing Sidewalk Maintenance through
Accurate Joint Deflection Measurement
Jisoo Park*, Seonghak Lee*, Paul Hyunbin Cho*, Zongkai Xiaโ€ , Loucif Hebbacheโ€ 
Collaboration: IRIS R&D Group Inc., Toronto, Canada
ICCE, 2025
pdf

The 43rd IEEE International Conference on Consumer Electronics (ICCE), Las Vegas, Nevada, USA, 2025
wildtalker WildTalker: Talking Portrait Synthesis in the Wild
Seonghak Lee*, Jisoo Park*, Junseok Kwonโ€ 
ECCV, 2024 workshop
project / pdf / code

The 18th European Conference on Computer Vision Workshop (ECCV workshop), 3D Modeling, Reconstruction, and Generation in the Wild, Milano, Italy, 2024
potf POTF: Prompt-based Object-centric Tensorial Field
Seonghak Lee*, Jisoo Park*, Junseok Kwonโ€ 
ICTC, 2024 workshop (Oral presentation)
pdf

The 15th International Conference on ICT Convergence (ICTC), Jeju Island, Korea, 2024
Journal
sota SOTA: Sequential Optimal Transport Approximation For Visual Tracking in Wild Scenario
Seonghak Lee, Jisoo Park, Radu Timofte, Junseok Kwonโ€ 
pdf

IEEE Access (ACCESS), Vol. 12, no. 1, page 177028-177037, 2024
Patent
  • Jinhee Park, Jisoo Park, Dagyeong Na, and Junseok Kwon. KOR Patent 10-2024-0096387, Deep Metric Learning Method for Similarities between Images Introducing Class-agnostic Features (July, 2024)
Awards
  • [2022] 3rd Place in SWยทAI Major Olympiad: Capstone Competition by Da Vinci Software Education Institute
  • [2021] 1st Place in SWยทAI Major Olympiad: Capstone Competition by Da Vinci Software Education Institute
  • [2021] 2nd Place in Software Talent Contest by Ministry of Science and ICT
  • [2020] Popularity Award in LINC+ Capstone Design Award by Korea Research Foundation

Last updated: Aug. 2025
Web page design credit to Jon Barron