Subject: Research Opportunities: Speech Recognition Technology / Speech From: Phil Green <p.green(at)dcs.shef.ac.uk> Date: Wed, 12 Jan 2000 16:16:05 +0000--- Apologies for multiple postings --- Postdoctoral or Postgraduate Research Opportunities AUTOMATIC SPEECH RECOGNITION FOR PEOPLE WITH SEVERE DYSARTHIA (STARDUST) ========================================================================= This project is to be funded by the UK National Health Service NEAT programme (New and Emerging Applications of Technology). It will be located jointly in the Speech and Hearing Research Group, Department of Computer Science, University of Sheffield, UK and in Barnsley District General Hospital. It will start in June 2000 or before and run for 36 months. It will employ * A Computer Scientist, preferably with experience in Speech Technology, * A Speech Therapist part-time These appointments may be at postgraduate or postdoctoral level. A postgraduate appointee will have the opportunity to study for a Ph.D. Salaries will be on UK Research Assistant or Clinical Scales, as appropriate. More details on request. STARDUST stands for Speech Training And Recognition for Dysarthic USer-controlled assistive Technology. Dysarthia is a common speech disorder which, in its severest form, results in unintelligible speech. This disorder is often associated with other general neuromotor disabilities. People with these disabilities may have difficulty in making themselves understood as well as in reliably controlling environmental and communication aids. This project will apply state-of-the-art Speech Technology research to the recognition of severely dysarthric speech. Off-the-shelf automatic speech recognition systems function poorly for these users because of the increased variability of their articulations compared to normal speech and the difficulty of finding suitable corpora for training the recogniser. To overcome these problems we will develop a software application which integrates three functions: a) Real-time audio-visual feedback to train dysarthric speakers to improve the consistency of their vocalisations. b) Speech recognition capability with improved tolerance to speech variability. c) The ability to tailor the package to the needs of the client: to modify the feedback as training proceeds and to construct new recognisers incrementally as data is collected. The speech recognition software application will then be deployed to control electronic assistive technology, either a communication aid or an environmental control system. STARDUST will therefore provide an accurate small-vocabulary recogniser for disordered speech, thus contributing to the independence of a group of people with severe disabilities. If you are interested, send your CV and the names of two referees to Phil Green (address below), preferably by e-mail. Indicate what you feel you would bring to the project and when you might be available. For more information, please contact either Phil Green, Dr. Mark Hawley (Tel: +44 (0) 1226 777726 mark.hawley(at)bdgh-tr.trent.nhs.uk) or Prof. Pam Enderby (Tel: +44 (0) 114 271 5916 p.m.enderby(at)shef.ac.uk =================================================== Professor Phil Green Speech and Hearing Research Group Department of Computer Science University of Sheffield Regent Court 211 Portobello St., Sheffield S1 4DP UK phone: (44) 114 22 21828 fax: (44) 114 22 21810 email: p.green(at)dcs.shef.ac.uk www: http://www.dcs.shef.ac.uk/people/P.Green/