Jaemin Jung
Ph.D. Student / Multimodal AI Lab
Korea Advanced Institute of Science and Technology (KAIST)
Email: jjm5811 [at] kaist.ac.kr
External Links: [Google Scholar] [LinkedIn]
About Me 😃
I am currently a Ph.D. student advised by Prof. Joon Son Chung in Electrical Engineering at KAIST.
My research interests are in the areas of generation AI. I am particularly interested in talking face generation and audio generation.
Research Interests 💻
Generation AI
Audio Generation
Talking face generation
Keyword spotting
Publications 📚
VoiceDiT: Dual-Condition Diffusion Transformer for Environment-Aware Speech Synthesis
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2025
Bridging the Gap between Audio and Text using Parallel-attention for User-defined Keyword Spotting
IEEE Signal Processing Letters, 2024
[ paper | code ]
VoxMM: Rich Transcription of Conversations in the Wild
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024
Metric Learning for User-Defined Keyword Spotting
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2023
Education 🏫
Integrated M.S. / Ph.D. in Electrical Engineering, KAIST (Mar. 2022 ~ )
Winter Course at Technische Universität Berlin (Jan. 2018 ~ Feb.2018)
B.S. in Electronics Engineering, Kyungpook National University (Mar.2016 ~ Feb.2020)
Experience
Research Student at Speech Recognition lab, Seoul National University (Jul. 2021 ~ Sep. 2021)
Specific domain adaptation
Speech recognition
Research Intern at Digital holography lab, Electronics and Telecommunications Research Institute (Jun. 2020 ~ Sep. 2020)
Depth measurement using fourier optics from Infocus and Outfocus images
Development of Digital Holographic Table-Top Display