About

I am a Ph.D. candidate in Artificial Intelligence at Music and Audio Research Group, Seoul National University. My research interests lie in efficient and robust speech processing. In particular, I am working on training acceleration and knowledge distillation (efficiency); uncertainty estimation and domain adaptation (robustness).

Education

[2021 - now]
Ph.D. in Artificial Intelligence, Seoul National University
Advisor : Prof. Kyogu Lee

[2017 - 2021]
B.S. in Systems Management Engineering, Sungkyunkwan University

Experience

[Sep 2023 - Feb 2024]
Research Intern, NAVER Papago

Selected Publications (google scholar)

• Fast Speech Foundation Model Distillation Using Interleaved Stacking [link]
  Eungbeom Kim, Kyogu Lee
  2026 INTERSPEECH
• Uncertainty-Aware Self-Training for CTC-Based Automatic Speech Recognition [link]
  Eungbeom Kim, Kyogu Lee
  2025 AAAI (Oral presentation)
• Guiding Frame-Level CTC Alignments Using Self-Knowledge Distillation [link]
  Eungbeom Kim, Hantae Kim, Kyogu Lee
  2024 INTERSPEECH
• Debiased Automatic Speech Recognition for Dysarthric Speech via Sample Reweighting with Sample Affinity Test [link]
  Eungbeom Kim*, Yunkee Chae*, Jaeheon Sim, Kyogu Lee
  2023 INTERSPEECH
• Exploring Train and Test-Time Augmentations for Audio-Language Learning [link]
  Eungbeom Kim*, Jinhee Kim*, Yoori Oh, Kyungsu Kim, Minju Park, Jaeheon Sim, Jinwoo Lee, Kyogu Lee
  2022 arXiv

Challenge

• Automated Audio Captioning Using Parameter Efficient Fine-Tuning and Merging for LLMs
  Eungbeom Kim, Jaeheon Sim, Jinwoo Lee, Kyogu Lee
  4th Place at Automated Audio Captioning on DCASE 2024

Academic Services

• Reviewer: NeurIPS (2025, 2026), ICML (2026), INTERSPEECH (2026)