Main navigation
- Programs
- Subjects
- Universities
- Destinations
- Advice
The Centre for Vision, Speech and Signal Processing (CVSSP) pioneers innovative technologies that push boundaries. Our work spans facial recognition for security and healthcare applications, along with 3D spatial audio and video-based reconstruction for film, gaming, and virtual reality effects. We're building intelligent systems capable of perceiving and interpreting their environment through sight and sound.
As one of Europe's most prominent audio-visual research teams, CVSSP has earned global recognition for our trailblazing work in machine perception. Our interdisciplinary group combines leading expertise in sound and vision technologies, comprising over 170 researchers supported by more than £30 million in research funding.
We drive innovation in audio-visual signal processing, computer vision, and machine learning, specializing in image, video, and audio applications. Our research spans multiple domains including digital signal processing, AI and machine learning, computer graphics, human-computer interaction, medical imaging, and multimedia data science.
Our PhD program requires up to four years of full-time study. Students submit a confirmation report after 12 months for evaluation by independent assessors, followed by thesis submission after a minimum three-year period.
Each candidate receives guidance from two Surrey-based academic supervisors, supplemented by external collaborators when needed. Your primary supervisor, a specialist in your research field, will provide regular progress monitoring. Supervisors assist in shaping research objectives, accessing resources, and navigating the PhD journey, with external experts sometimes joining to offer specialized knowledge or organizational connections.