Ji Won Yoon (윤지원)
Assistant Professor @ Department of Artificial Intelligence, Chung-Ang University
Email: jiwonyoon (at) cau.ac.kr
Research Interests
Speech & Audio Processing
Natural Language Processing
On-device AI
Assistant Professor @ Department of Artificial Intelligence, Chung-Ang University
Email: jiwonyoon (at) cau.ac.kr
Research Interests
Speech & Audio Processing
Natural Language Processing
On-device AI
Ph.D. in Electrical and Computer Engineering, Seoul National University (SNU), February 2024
Advisor: Professor Nam Soo Kim
M.S. in Electrical and Computer Engineering, Seoul National University (SNU), February 2020
Advisor: Professor Nam Soo Kim
B.S. in Electrical Engineering, Korea University, February 2018
Distinguished Ph.D. Dissertation Award, February 2024
Seoul National University-Samsung Electronics Patent Award, August 2022
BK21 Outstanding Research Talent Fellowship, November 2021
Seoul National University-Samsung Electronics Paper Award, September 2021
2025
CCQA: Generating Question from Solution Can Improve Inference-Time Reasoning in SLMs
J. Kim and J. W. Yoon* (corresponding author)
EMNLP (main) 2025
Heuristic-free Knowledge Distillation for Streaming ASR via Multi-modal Training
J. W. Yoon
AAAI 2025
FADEL: Uncertainty-aware Fake Audio Detection with Evidential Deep Learning (Oral presentation)
J. Y. Kang, J. W. Yoon, S. Kim, M. H. Han, and N. S. Kim
ICASSP 2025
2024
HuBERT-EE: Early Exiting HuBERT for Efficient Speech Recognition (Oral presentation)
J. W. Yoon, B. J. Woo, and N. S. Kim
Interspeech 2024
Towards Maximum Likelihood Training for Transducer-based Streaming Speech Recognition
H. Lee, J. W. Yoon, S. Kim, and N. S. Kim
IEEE Signal Processing Letters
J. W. Yoon, H. Lee, J. Kang, and N. S. Kim
IEEE Access
Gene-Gene Relationship Modeling Based on Genetic Evidence for Single-Cell RNA-Seq Data Imputation
D. Um, J. W. Yoon, S. J. Ahn and Y. Yeo
NeurIPS 2024
Unseen Road Type Detection in Road Networks for Intelligent Transportation Systems
D. Um, Y. Yeo, J. W. Yoon, and J. Y. Choi
IEEE ITSC 2024
EEND-EM: End-to-End Neural Speaker Diarization with EM-Network
B. J. Woo, J. W. Yoon, M. H. Han, C. Y. Moon, and N. S. Kim
APSIPA ASC 2024
2023
J. W. Yoon, S. Ahn, H. Lee, M. Kim, S. M. Kim, and N. S. Kim
ICML 2023
J. W. Yoon, H. Y. Kim, H. Lee, S. Ahn, and N. S. Kim
IEEE/ACM Transactions on Audio, Speech, and Language Processing
J. W. Yoon, S. M. Kim, and N. S. Kim
Interspeech 2023
2022
J. W. Yoon, B. J. Woo, S. Ahn, H. Lee, and N. S. Kim
IEEE SLT 2022
2021
J. W. Yoon, H. Lee, H. Y. Kim, W. I. Cho, and N. S. Kim
IEEE/ACM Transactions on Audio, Speech, and Language Processing
H. Y. Kim, J. W. Yoon, W. I. Cho, and N. S. Kim
IEEE Signal Processing Letters
H. Y. Kim, J. W Yoon, S. J. Cheon, W. H. Kang, and N. S. Kim
Applied Sciences
2020
W. I. Cho, D. Kwak, J. W. Yoon, and N. S. Kim
Interspeech 2020
윤지원, 김진영. 소형 언어 모델의 추론 능력 향상 방법, 출원번호 10-2025-0073024, 출원일자 2025년 06월 04일.
윤지원, 서은서. 딥보이스 탐지 방법 및 장치, 출원번호 10-2025-0060863, 출원일자 2025년 05월 12일.
김남수, 윤지원. 효율적인 음성 인식을 위한 음성 자기지도 학습 모델의 조기 종료 시스템 및 방법, 출원번호 10-2023-0180207, 출원일자 2023년 12월 13일.
김남수, 윤지원. 음성 처리 방법 및 장치, 출원번호 10-2023-0152826, 출원일자 2023년 11월 7일.
Nam Soo Kim, Ji Won Yoon. Method and apparatus with neural network training, 미국특허, 출원번호 18/108,727, 출원일자 2023년 02월 13일.
김남수, 윤지원. 인공 신경망 모델의 동작 방법 및 장치. 출원번호 10-2022-0105734. 출원일자 2022년 08월 23일.
Nam Soo Kim, Ji Won Yoon. Method and apparatus with abnormal channel of microphone array detection and compensation signal generation, 미국특허, 등록번호 US 12,342,149 B2, 등록일자 2025년 06월 24일.
김남수, 윤지원. 마이크 어레이의 이상 채널 검출 및 보상 신호 생성 방법 및 장치. 출원번호 10-2021-0132102. 출원일자 2021년 10월 06일.
[The Korean Institute of Broadcast and Media Engineers] 2025 Fall Workshop on Broadcasting and Media Technologies
The Evolution of Deepfake Audio Detection
October 2025
Samsung Electronics MX Division
SpeechLLM: The Evolution of Conversational AI
October 2025
University of Seoul
Special Lecture on Automatic Speech Recognition
September 2025
Samsung Electronics MX Division
Towards Lightweight and Efficient Sequence Models
June 2025
[The Korean Society of Speech Sciences] Spring Conference Keynote
Special Lecture: Model Compression and Early-Exit Techniques for Efficient Automatic Speech Recognition
May 2025
Sogang University
Towards Lightweight and Efficient Sequence Models
January 2025
42dot
Towards Lightweight and Efficient Sequence Models
January 2025
Sungkyunkwan University
AI with Speech Signal Processing
September 2024