Current

Ongoing Projects

Active research programmes with open questions and upcoming results.

SignGPT
SignGPT
UKRI EPSRC Programme Grant
Active

SignGPT is a UKRI EPSRC Programme Grant focused on the development of an AI-powered translation system capable of unconstrained, bidirectional translation between British Sign Language (BSL) and English. The project will build the first generative predictive transformer for sign language, combining computer vision, sign linguistics, and machine learning. It is led by an interdisciplinary team from the University of Surrey, University of Oxford, and University College London, with direct involvement from Deaf organisations and community partners.

BSL ↔ English Translation Generative Transformers Sign Linguistics Computer Vision Deaf Community
UKRI EPSRC University of Surrey University of Oxford UCL
Project Page
Google AI Grant
Google.org Philanthropic Grant
Active

Grant funding and additional support from Google's philanthropic arm, Google.org, to develop artificial intelligence research paving the way for instant sign language translation. Working with Signapse as a delivery partner, the project translates key websites into sign language, boosting digital inclusion for the 600,000 Deaf people in the US and UK for whom sign language is their first language.

Instant SL Translation Digital Inclusion Web Accessibility BSL · ASL
Google.org Signapse AI (delivery partner)
Project Page
UMCS
UKRI EPSRC · JST UK-Japan Research Project
Active

Understanding Multilingual Communication Spaces (UMCS) is a £3.5 million UK-Japan research project developing human-centred AI and augmented reality systems for real-time translation across British Sign Language, Japanese Sign Language, English and Japanese. The project focuses on authentic Deaf-to-Deaf conversations, capturing natural interaction patterns such as turn-taking, backchannels, repair strategies and shared visual attention, rather than relying only on interpreter-facing video data.

Real Deaf Conversations Human-Centred AI Augmented Reality BSL · JSL Multimodal Translation
UKRI EPSRC Japan Science and Technology Agency Signapse AI NHK Enterprises
Project Page
Completed

Prior Projects

Projects that have concluded, with released datasets, code, and papers.

IICT Flagship
Swiss National Funded Flagship Project
Finishing

The goal of the IICT Flagship is to develop information and communication technologies (ICT) for persons with disabilities. The flagship targets five applications in the context of accessibility: text simplification, sign language translation, sign language assessment, audio description, and spoken subtitles. Each application constitutes its own subproject, with tight connections through shared AI technologies. The University of Surrey is included due to its extensive expertise in AI for sign languages.

Sign Language Translation Sign Language Assessment Text Simplification Audio Description Spoken Subtitles Accessibility
Swiss National Funding University of Surrey
Project Page
SMILE
Swiss Funded Research Project
Finishing

The goal of SMILE is to pioneer an assessment system for Swiss German Sign Language (Deutschschweizerische Gebärdensprache, DSGS) using automatic sign language recognition technology. The project develops robust recognition models tailored to DSGS and integrates them into a learner assessment framework to support Deaf education and sign language acquisition.

Swiss German Sign Language (DSGS) Sign Language Recognition Learner Assessment Deaf Education
Swiss National Funding
Project Page
Learning to Recognise Dynamic Visual Content from Broadcast Footage
Research Project
Completed

This project tackled the challenge of automatically learning to recognise dynamic activity in broadcast footage, with demonstration activities in both sign language and more general actions and activity. The work developed methods for weakly supervised activity recognition from large-scale broadcast data, bridging the gap between constrained lab settings and real-world video.

Sign Language Recognition Action Recognition Broadcast Footage Weakly Supervised Learning
Making Sense
Research Project
Completed

Making Sense focused on improving investigative capability through the application of science and technology. The project explored how advanced computer vision and machine learning techniques can be applied to support investigative processes, including the analysis of visual content at scale.

Visual Intelligence Investigative Capability Computer Vision
DictaSign
EU Funded Research Project
Completed

DictaSign aimed to enable communication between Deaf individuals by promoting the development of natural human computer interfaces (HCI) for Deaf users. It researched and developed recognition and synthesis systems for sign languages at a level of detail necessary for recognising and generating authentic signing. Research outcomes were integrated into three prototypes: a Search-by-Example tool, a Sign Language-to-Sign Language translator, and a sign Wiki — enabling knowledge-sharing within and across Deaf communities.

SL-to-SL Translation Sign Recognition Sign Synthesis HCI for Deaf Sign Wiki Search-by-Example
European Union
Paper