Multimodal AI Lab
School of Electrical Engineering, KAIST


We are looking for motivated students in machine learning, speech processing and computer vision. Please read this page for more information.
We will be hosting the fourth VoxCeleb Speaker Recognition Challenge (VoxSRC) in Incheon, South Korea this autumn. You can find out more about the challenge here and the dataset here.

Current research

Project image
Speech recognition
Project image
Project image
Speaker diarisation
Project image
Sign language and gesture recognition

KAIST logo