Research Fellow

Audio-Visual Speech Separation

Centre for Vision Speech and Signal Processing (CVSSP)

Salary: £28,983 - £33,600 per annum
(Subject to qualifications and experience)

Applications are invited for a 30 months postdoctoral research fellow position available at CVSSP, starting on Friday, October 1, 2010. The research fellow is expected to work on a recently funded EPSRC project, entitled "Audio and video based speech separation for multiple moving sources within a room environment". This is a collaborative project with Loughborough University. The project aims to investigate the problem of separating multiple moving sources from convolutive speech mixtures in an indoor environment using the additional information from video signals. The research focus at Surrey will be on the algorithm development for visual localisation and tracking of multiple moving speakers in video. The visual information will then be combined with the audio modality to assist the separation of speech sources from the reverberant mixtures based on the coherence betwen the bi-modalities of audio and visual speech.

Successful applicants will join the CVSSP, a leading research group in sensory (visual and auditory) data analysis and interpretation. CVSSP is one of the largest UK research groups in machine vision and audition with more than 110 researchers. It also has world-class audio and video facilities that are uniquely placed for performing research in this area. CVSSP forms part of the Department of Electronic Engineering, which received one of the highest ratings (joint second position across the UK) in the last research quality assessment, i.e. 2008 RAE, with 70% of its research classified as either 4* ("world-leading") or 3* ("internationally excellent"). As an additional benefit, the successful applicant has the opportunity to work with researchers at the Advanced Signal Processing Group, Loughborough University, UK, and the GIPSA Lab, Grenoble, France.

Applicants should have a PhD degree or equivalent in electrical and electronic engineering, computer science, mathematical science, statistics, physics, or related disciplines. Applicants should be able to demonstrate excellent mathematical, analytical and computer programming skills. Advantages will be given to the applicants who have experience in visual tracking, multimodal signal processing, blind source separation, and/or machine learning.

For informal inquiries about the position, please contact Dr Wenwu Wang ( or Prof Josef Kittler (

For an application pack and to apply on-line please go to our website: If you are unable to apply on-line please contact Miss Stacey Michaelides, HR Assistant on Tel: +44 (0) 1483 686106 or email:

The closing date for applications is Monday August 9th, 2010. (Suitable candidates will be shortlisted within one week of the closing date.)

For further information about the University of Surrey, please visit

We acknowledge, understand and embrace cultural diversity.