<aside>
<img src="/icons/card_orange.svg" alt="/icons/card_orange.svg" width="40px" />
Occupation: Research Scientist
Affiliation:
-
Postdoctoral research fellow,
Music and Audio Research Group (MARG), Seoul National University, South Korea
Research Area:
- Voice Conversion
- Speech processing
- Multi-modal association
Contact:
✉️ [email protected]
:linkedin: LinkedIn
</aside>
<aside>
<img src="/icons/book-closed_blue.svg" alt="/icons/book-closed_blue.svg" width="40px" /> Papers
- “Toward Open-Set Speaker Attribute Prediction with Keyword-Appended LLM Embeddings”
Byoungjun So, Jaejun Lee and Kyogu Lee, Interspeech 2026 (Accepted)
- “TAP-ETS: Time Aligned Phoneme Guiding for EMG-to-Speech Synthesis”
Dongyub Han, Injune Hwang, Jaejun Lee, Jiwon Lee, and Kyogu Lee, Interspeech 2026 (Accepted)
- “Enhancing EMG-to-Speech via Silent-Voiced Representation Alignment”
Jiwon Lee, Injune Hwang, Jaejun Lee, Eungbeom Kim, Dongyeop Han and Kyogu Lee, Interspeech 2026 (Accepted)
- “GETS: Guiding EMG-to-Speech Synthesis via Silent Speech Recognition”
Jiwon Lee, Jaejun Lee and Kyogu Lee, Interspeech 2026 (Accepted)
- “EMG-to-Speech with Fewer Channels”
Injune Hwang, Jaejun Lee and Kyogu Lee, ICASSP 2026 (Paper)
- “LipSody: Lip-to-Speech Synthesis with Enhanced Prosody Consistency”
Jaejun Lee, Yoori Oh, and Kyogu Lee, ICASSP 2026 (Paper, Demo)
- “Vo-Ve: An Explainable Voice-Vector for Speaker Identity Evaluation”
Jaejun Lee and Kyogu Lee, Interspeech 2025 (Paper, Github)
- “Speaking Without Sound: Multi-speaker Silent Speech Voicing with Facial Inputs Only”
Jaejun Lee, Yoori Oh, and Kyogu Lee, ICASSP 2025 (Paper, Demo)
- “Hear Your Face: Face-based voice conversion with F0 estimation”
Jaejun Lee, Yoori Oh, Injune Hwang, and Kyogu Lee, Interspeech 2024 (Paper, Demo, Github)
- “Room Adaptive Conditioning Method for Sound Event Classification in Reverberant Environments”
Jaejun Lee, Donmoon Lee, Hyeongseok Choi, ICASSP 2021 (Paper)
- “Enhancing Music Features by Knowledge Transfer from User-item Log Data”
Donmoon Lee, Jaejun Lee, Jeongsoo Park, and Kyogu Lee, ICASSP 2019 (Paper)
- “Convolutional neural network based traffic sound classification robust to environmental noise”
Jaejun Lee, Wansoo Kim, and Kyogu Lee, The Journal of the Acoustical Society of Korea 37.6 2018 (Paper)
</aside>
<aside>
<img src="/icons/groups_green.svg" alt="/icons/groups_green.svg" width="40px" /> Projects
Voice Conversion Tutorial
EMG-based speech generation
Music Auto-tagging
Urban sound detection and classification
</aside>
<aside>
<img src="/icons/trophy_yellow.svg" alt="/icons/trophy_yellow.svg" width="40px" /> Awards
2025년 AI 챔피언 대회 (TTA 회장상)
2021 인공지능 그랜드 챌린지 (과학기술정보통신부 장관상)
</aside>
<aside>
<img src="/icons/briefcase_pink.svg" alt="/icons/briefcase_pink.svg" width="40px" /> Biography
- Music and Audio Research Group, Seoul National University, South Korea
Post-doctoral Research Fellow | Sep 2025 -
- Music and Audio Research Group, Seoul National University, South Korea
Research Scientist | Sep 2017 - Aug 2025
- SUPERTONE.AI (Internship), South Korea
Research Scientist | Jul 2021 - Aug 2021
- CHEMTRONICS CORPORATION, South Korea
Product Management | Apr 2011 - Mar 2014
</aside>
<aside>
<img src="/icons/graduate_purple.svg" alt="/icons/graduate_purple.svg" width="40px" /> Education
- DOCTOR OF INTELLIGENCE AND INFORMATION MAJOR,
GRADUATE SCHOOL OF CONVERGENCE SCIENCE AND TECHNOLOGY
Seoul National University | 2019 - 2025
- MASTER OF INTELLIGENCE AND INFORMATION MAJOR,
GRADUATE SCHOOL OF CONVERGENCE SCIENCE AND TECHNOLOGY
Seoul National University | 2017 - 2019
- BACHELOR OF SCIENCE IN ELECTRONIC AND ELECTRICAL ENGINEERING,
COLLEGE OF INFORMATION AND COMMUNICATION ENGINEERING
Sungkyunkwan University | 2010 - 2017
</aside>