Youngjoon Jang
Contact: jyj [at] mmai.io

Room #3103, N24 Bldg, KAIST.
I am a Ph.D. student advised by Prof. Joon Son Chung at KAIST. I earned my M.S. supervised by Prof. In So Kweon at KAIST. I was a visiting student at VGG Group, University of Oxford, under the supervision of Prof. Andrew Zisserman.
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
-
ICASSPVoiceDiT: Dual-Condition Diffusion Transformer for Environment-Aware Speech SynthesisIn International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2025.
-
ACMMMLet Me Finish My Sentence: Video Temporal Grounding with Holistic Text UnderstandingIn ACM International Conference on Multimedia (ACMMM), 2024.
-
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.
Honors and Awards
Jun 2023 | Top 3% Recognition Certificates, ICASSP 2023 [Certificate] |
---|