EPSRC logo

Details of Grant 

EPSRC Reference: GR/N09725/01
Title: PUMA: PERSONALISED USER INTERFACES FOR INFORMATION MANAGEMENT AND AUTHORISATION
Principal Investigator: Russell, Professor M
Other Investigators:
Quigley, Dr SF
Researcher Co-Investigators:
Project Partners:
BT Ensigma Ltd Snape Signals Research
Department: Electronic, Electrical and Computer Eng
Organisation: University of Birmingham
Scheme: LINK
Starts: 01 June 2000 Ends: 31 May 2003 Value (£): 147,415
EPSRC Research Topic Classifications:
Artificial Intelligence Human Communication in ICT
EPSRC Industrial Sector Classifications:
Aerospace, Defence and Marine Communications
Financial Services Creative Industries
Retail
Related Grants:
Panel History:  
Summary on Grant Application Form
The convergence of the mobile phone and data terminal will result in ubiquitous integrated devices for communications, e-commerce, distance learning and internet access. These will be portable, personal and may contain proprietary information. The technology to build them largely exists, but fraud-resistant and effective human-machine interaction presents unique and unsolved problems.The project addresses speech, keyboard and command-button interaction with a personal computer assistant. The objective is to exploit user and domain knowledge to optimise human-machine interaction and provide a novel approach to robust fraud control.Statistical techniques will be applied at all levels of an interaction. For spoken language, transaction recognition and user authentification will involve analysis of the acoustic signal, word usage, syntactic structure, synonym usage and the likelihood of a particular transaction. The necessary constraints will emerge from ongoing personalisation of the integrated system. The project will combine statistical methods from speech recognition, topic spotting, language processing and information retrieval into a trainable 'hidden thesaurus model', in which the relationships between user input and database entries are regulated by an intermediate, probabilistic thesaurus, while methods such as Latent Semantic Analysis will capture and represent knowledge of typical user transactions.
Key Findings
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
Potential use in non-academic contexts
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
Impacts
Description This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
Summary
Date Materialised
Sectors submitted by the Researcher
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
Project URL:  
Further Information:  
Organisation Website: http://www.bham.ac.uk