Youngjoon Jang

Contact: jyj [at] mmai.io

jyj.jpeg
Room #3103, N24 Bldg, KAIST.

I am currently a Ph.D. student advised by Prof. Joon Son Chung, in Division of Future Vehicle at Korea Advanced Institute of Science and Technology (KAIST). Previously, I earned my M.S. in Division of Future Vehicle from KAIST (Feb. 2022) and B.S. in Division of Robotics from Kwangwoon University (Feb. 2020).

My research aims to effectively train deep neural networks with multi-modality (vision, audio and text). Also, I have an interest in techniques related to sign language for helping deaf people.

Publications

  1. CVPR
    Faces that Speak: Jointly Synthesising Talking Face and Speech from Text
    { Youngjoon JangJi-Hoon Kim}*Junseok Ahn, Doyeop Kwak, Hongsun Yang, Yooncheol Ju, ILHWAN KIM, Byeong-Yeol Kim, and Joon Son Chung  (*: equal contributions)
    In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024.
  2. ICASSP
    Slowfast Network for Continuous Sign Language Recognition
    {Junseok Ahn,  Youngjoon Jang}*and Joon Son Chung  (*: equal contributions)
    In International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2024.
  3. ICASSP
    VoxMM: Rich Transcription of Conversations in the Wild
    {Doyeop Kwak, Jaemin Jung}*Kihyun Nam,  Youngjoon JangJee-weon Jung, Shinji Watanabe, and Joon Son Chung  (*: equal contributions)
    In International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2024.
  4. ICASSP
    FreGrad: Lightweight and Fast Frequency-aware Diffusion Vocoder
    {Tan Dat Nguyen, Ji-Hoon Kim}* Youngjoon JangJaehun Kim, and Joon Son Chung  (*: equal contributions)
    In International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2024.
  5. ICASSP
    TalkNCE: Improving Active Speaker Detection with Talk-aware Contrastive Learning
    {Chaeyoung Jung, Suyeon Lee}*Kihyun Nam, Kyeongha Rho, You Jin Kim,  Youngjoon Jangand Joon Son Chung  (*: equal contributions)
    In International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2024.
  6. ICASSP
    Seeing Through the Conversation: Audio-visual Speech Separation based on Diffusion Model
    {Suyeon Lee, Chaeyoung Jung}* Youngjoon JangJaehun Kim, and Joon Son Chung  (*: equal contributions)
    In International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2024.
  7. ACMMM
    That’s What I Said: Fully-Controllable Talking Face Generation
    { Youngjoon JangKyeongha Rho}*Jongbhin Woo, Hyeongkeun Lee, Jihwan Park, Youshin Lim, Byeong-Yeol Kim, and Joon Son Chung  (*: equal contributions)
    In ACM International Conference on Multimedia, 2023.
  8. ICASSP
    Self-Sufficient Framework for Continuous Sign Language Recognition
    Youngjoon JangYoungtaek OhJae Won ChoMyungchul Kim, Dong-Jin KimIn So Kweon, and Joon Son Chung
    In International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2023.
  9. ICASSP
    Metric Learning for User-Defined Keyword Spotting
    {Jaemin Jung, Youkyum Kim}*Jihwan Park, Youshin Lim, Byeong-Yeol Kim,  Youngjoon Jangand Joon Son Chung  (*: equal contributions)
    In International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2023.
  10. BMVC
    Signing Outside the Studio: Benchmarking Background Robustness for Continuous Sign Language Recognition
    Youngjoon JangYoungtaek OhJae Won ChoDong-Jin KimJoon Son Chungand In So Kweon
    In British Machine Vision Conference (BMVC), 2022.
  11. FG
    KSL-Guide: A Large-scale Korean Sign Language Dataset Including Interrogative Sentences for Guiding the Deaf and Hard-of-Hearing
    Soomin Ham, Kibaek Park,  Youngjoon JangYoungtaek OhSeokmin Yun, Sukwon Yoon, Chang Jo Kim, Han-Mu Parkand In So Kweon
    In International Conference on Automatic Face and Gesture Recognition (FG), 2021.