Regular biography
Joon Son Chung is a faculty member in the School of Electrical Engineering at KAIST. Their research focuses on multimodal AI, with an emphasis on machine learning, speech processing, and computer vision. Chung leads the Multimodal AI Lab at KAIST, where they explore topics such as speech generation, talking face synthesis, audio-visual speech separation, and sound source localization. Their work has been published in top conferences such as AAAI, ICASSP, ACMMM, and ICCV. For more information, visit their lab website at https://mm.kaist.ac.kr/.
Scholar-generated biography
Joon Son Chung is a researcher specializing in machine learning, speech processing, and computer vision. Their work focuses on advancing speaker recognition, audio-visual speech recognition, and anti-spoofing techniques. Chung has contributed to large-scale datasets such as VoxCeleb and LRS3-TED, which are widely used in speech and visual recognition research. Their publications explore deep learning methods for speaker verification, lip reading, and audio-visual speech enhancement. Chung's research emphasizes robust and scalable solutions for real-world applications, including automated lip sync and speaker diarization. Their work has been recognized through various publications and contributions to the field of multimodal signal processing.