Youngjoon Jang
Contact: jyj [at] mmai.io
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
-
CVPRFaces that Speak: Jointly Synthesising Talking Face and Speech from TextIn IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024.
-
ICASSPVoxMM: Rich Transcription of Conversations in the WildIn International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2024.
-
ICASSPFreGrad: Lightweight and Fast Frequency-aware Diffusion VocoderIn International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2024.
-
ICASSPTalkNCE: Improving Active Speaker Detection with Talk-aware Contrastive LearningIn International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2024.
-
ICASSPSeeing Through the Conversation: Audio-visual Speech Separation based on Diffusion ModelIn International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2024.