Hye-jin Shim

Bio

◆ Current: Postdoctoral researcher, LTI @Carnegie Mellon University (Pittsburgh, USA) - PI: Shinji Watanabe

◆ Postdoctoral researcher, School of Computing @University of Eastern Finland (Joensuu, Finland) - PI: Tomi Kinnunen

◆ PhD, School of Computer Science @University of Seoul (Seoul, Korea) - Supervisor: Ha-Jin Yu

◆ MS, School of Computer Science @University of Seoul (Seoul, Korea) - Supervisor: Ha-Jin Yu

◆ BCom, the Department of International Trade @Kwangwoon University (Seoul, Korea)

Updates

◆ I’m currently exploring opportunities for faculty positions in academia as well as research scientist roles. Please feel free to reach out if you know of any openings or would like to connect!

Selected Publications - Latest 1st authored papers

a-DCF: an architecture agnostic metric with application to spoofing-robust speaker verifications
[code] Odyssey, 2024
Hye-jin Shim, Jee-weon Jung, Tomi Kinnunen, Nicholas Evans, Jean-Francois Bonastre, and Itshak Lapidot
Used as a primary evaluation metrics in ASVspoof5 challenge

How to Construct Perfect and Worse-than-Coin-Flip Spoofing Countermeasures: A Word of Warning on Shortcut Learning Interspeech, 2023
Hye-jin Shim, Jee-weon Jung, and Tomi Kinnunen

Multi-Dataset Co-Training with Sharpness-Aware Optimization for Audio Anti-spoofing Interspeech, 2023
Hye-jin Shim, Rosa González Hautamäki, Md Sahidullah, and Tomi Kinnunen

Graph attentive feature aggregation for text-independent speaker verification ICASSP, 2022
Hye-jin Shim*, Jungwoo Heo*, Jae-Han Park, Ga-Hui Lee, and Ha-Jin Yu

Community Engagements

Conference Review: Interspeech, ICASSP, Odyssey, ASRU, SLT

Journal Review: Computer Speech & Language(CSL), Transactions on Audio, Speech, and Language Processing (TASLP), Speech Communications, Digital Signal Processing, Pattern Recognition Letters, Applied Acoustics

Challenge Organizer: ASVspoof5 Challenge, Spoofing‑Aware Speaker Verification Challenge

Session Chair: Spoofing‑Aware Speaker Verification(Special Session), Interspeech