Ph.D./MS Student @POSTECH NLP LAB

Automatic Speech Recogntion (ASR), Multilingual ASR, MLops, Kubernetes

2021.Feb - now POSTECH, Pohang (Korea) Ph.D./M.S. Degree (Computer Science and Engineering)

2017 - 2021 Sejong University, Seoul (Korea) B.S. Degree (Software Engineering & Data Science)

한국어 인공지능 경진대회 (음성인식)

• Korean Artificial Intelligence Contest (Speech Recognition) Grand Prize (2nd), Minister's Award, Ministry of Science and ICT, Republic of Korea [link] [link], 최우수상, 과기정통부 장관상, 2022

• Korean Artificial Intelligence Contest (Speech Recognition) 5th Ranked, Director's Award, National Information Society Agency (NIA), Republic of Korea [link], 장려상, 지능정보원(NIA) 원장상, 2023

• Korean Artificial Intelligence Contest (Speech Recognition) 4th Ranked, Director's Award, National Information Society Agency (NIA), Republic of Korea [link], 장려상, 지능정보원(NIA) 원장상, 2021

Conference

• Best Paper Nominee in SiGDial 2024: Enhancing Dialogue Speech Recognition with Robust Contextual Awareness via Noise Representation Learning Wonjun Lee*, San Kim* and Gary Geunbae Lee [link]

• DyPCL: Dynamic Phoneme-level Contrastive Learning for Dysarthric Speech Recognition [link]

  Wonjun Lee*, Solee Im*, Heejin Do, Yunsu Kim, Jungseul Ok, Gary Geunbae Lee

  🇺🇸 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics (NAACL), 2025, Albuquerque, New Mexico, USA

• Enhancing Dialogue Speech Recognition with Robust Contextual Awareness via Noise Representation Learning [link] [link]

  Wonjun Lee*, San Kim*, Gary Geunbae Lee

  🇯🇵 ACL/ISCA Special Interest Group on Discourse and Dialogue (SIGDial), 2024, Kyoto, Japan

• An Investigation Into Explainable Audio Hate Speech Detection [link]

  Wonjun Lee*, Jinmyeong An*, Yejin Jeon, Jungseul Ok, Yunsu Kim, Gary Geunbae Lee

  🇯🇵 ACL/ISCA Special Interest Group on Discourse and Dialogue (SIGDial), 2024, Kyoto, Japan

• Acoustic Feature Mixup for Balanced Multi-aspect Pronunciation Assessment [link]

  Heejin Do, Wonjun Lee, Gary Geunbae Lee

  🇬🇷 INTERSPEECH, 2024, Kos Island, Greece

• Optimizing Two-Pass Cross-Lingual Transfer Learning: Phoneme Recognition and Phoneme to Grapheme Translation [link]

  Wonjun Lee, Yunsu Kim and Gary Geunbae Lee

  🇹🇼 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), 2023, Taipei, Taiwan

• Exploring the Viability of Synthetic Audio Data for Audio-Based Dialogue State Tracking [link]

  Jihyun Lee*, Yejin Jeon*, Wonjun Lee, Yunsu Kim and Gary Geunbae Lee

  🇹🇼 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), 2023, Taipei, Taiwan

• How to Use Speech Related Digital Biomarkers in Patients With Depressive Disorder [link]

  Wonjun Lee*, Seungyeon Seo*, Hyun Jeong Kim

  🇰🇷 Digital Health Research (Korean Society of Digital Health)

• 한국어 자모단위 음성인식 결과 후보정을 위한 신경망 기반 자모 병합 방법론

  임솔이*, 이원준*, 이근배, 김윤수

  🍊 제35회 한글 및 한국어 정보처리 학술대회논문집 (HCLT), 2023, 제주, 대한민국

• 다국어 음성인식을 위한 언어별 출력 계층 구조 Wav2Vec2.0

  이원준, 이근배

  🇰🇷 제33회 한글 및 한국어 정보처리 학술대회 논문집 (HCLT), pp. 414-418, 2021

• Keyword-Aware ASR Error Augmentation for Robust Dialogue State Tracking [link]

  Jihyun Lee, Solee Im, Wonjun Lee, Gary Geunbae Lee

  📄 Preprint, Arxiv.

• Method and Apparatus for Multilingual Speech Recognition based on Artificial Intelligence Models, U.S. , 17/954,185