Deep learning for sign language recognition and translation

The project will research and develop new approaches at the interface between computer vision and neural machine translation with the fundamental goal of addressing automatic recognition and translation of sign language to spoken language. In addition to excellent numerical and programming skills, previous experience in deep learning, NMT, computer vision and sign language would be highly advantageous.

This project is under the supervision of Professor Richard Bowden who runs the cognitive vision lab within the Centre for Vision Speech and Signal Processing. He has a long-standing international track record of work covering many areas of computer vision and machine learning which include visual tracking and the location, tracking, and understanding of humans. You will be joining a thriving research group with ongoing projects into perception for autonomous vehicles, sign language recognition/production and robotics and AI.

We acknowledge, understand and embrace diversity.

All applicants should have (or expect to obtain) a first-class degree in a numerate discipline (mathematics, science or engineering) or MSc with Distinction (or 70% average) and a strong interest in pursuing research in this field. Additional experience which is relevant to the area of research is also advantageous.

Non-native English speakers will be required to have IELTS 6.5 or above (or equivalent) with no sub-test of less than 6.

Centre for Vision, Speech and Signal Processing (CVSSP)