Member image
Jaehun Kim
Ph.D. Student
School of Electrical Engineering, KAIST

About me

I am a Ph.D. student at KAIST, advised by Professor Joon Son Chung.

My research interests lie in multimodal generative AI: audio-visual learning, speech synthesis

Experience

Research Intern, Multimodal AI Lab (MMAI)

Jun. 2022 - Feb. 2023

Advisor: Joon Son Chung

Research Intern, INNERVERZ, Korea

Apr. 2022 - Jul. 2022

Speech synthesis for virtual avatar

Research Intern, Music and Audio Research Group (MARG), SNU

Jan. 2022 - Feb. 2022

Advisor: Kyogu Lee

AI Research Head, ReliefMind, Korea

Jul. 2021 - Oct. 2021

Life assistant for mental health patients with speech AI diagnostics

Research Intern, Music and Audio Computing (MAC) Lab, KAIST

Jun. 2021 - Jul. 2021

Advisor: Juhan Nam

Intern, NAVER Audio Platform, Korea

Sep. 2020 - Feb. 2021

Research Intern, Smart Sound Lab, KAIST

Dec. 2019 - Aug. 2020

Advisor: Jungwoo Choi

Education

Ph.D. in Electrical Engineering, KAIST

Mar. 2025 - present

Advisor: Joon Son Chung

M.S. in Future Vehicle, KAIST

Mar. 2023 - Feb. 2025

Advisor: Joon Son Chung

B.S. in Electrical Engineering, KAIST

Sep. 2017 - Feb. 2023

Publications

2025

Thumbnail
SPADE: Structured Pruning and Adaptive Distillation for Efficient LLM-TTS
Tan Dat Nguyen, Jaehun Kim, Ji-Hoon Kim, Shukjae Choi, Youshin Lim, Joon Son Chung
ICASSP
Paper Demo
Thumbnail
SCORE: Scaling audio generation using Standardized COmposite REwards
Jaemin Jung*, Jaehun Kim*, Inkyu Shin, Joon Son Chung
under review
Paper Demo
Thumbnail
Dub-S2ST: Textless Speech-to-Speech Translation for Seamless Dubbing
Jeongsoo Choi*, Jaehun Kim*, Joon Son Chung
EMNLP
Paper
Thumbnail
AdaptVC: High Quality Voice Conversion with Adaptive Learning
Jaehun Kim, Ji-Hoon Kim, Yeunju Choi, Tan Dat Nguyen, Seongkyu Mun, Joon Son Chung
ICASSP
Paper Demo Code

2024

Thumbnail
Fregrad: Lightweight and fast frequency-aware diffusion vocoder
Tan Dat Nguyen, Ji-Hoon Kim, Youngjoon Jang, Jaehun Kim, Joon Son Chung
ICASSP
Paper Demo Code
Thumbnail
Seeing through the conversation: Audio-visual speech separation based on diffusion model
Suyeon Lee, Chaeyoung Jung, Youngjoon Jang, Jaehun Kim, Joon Son Chung
ICASSP
Paper Demo Code
Thumbnail
Let there be sound: Reconstructing high quality speech from silent videos
Ji-Hoon Kim*, Jaehun Kim*, Joon Son Chung
AAAI
Paper Demo

Contact

  kjaehun (at) kaist.ac.kr
  Room 3103, N24 (LG Innovation Hall)
KAIST logo