Founded in 1984, CSTR is concerned with research in all areas of speech technology including speech recognition, speech synthesis, speech signal processing, information access, multimodal interfaces and dialogue systems. We have many collaborations with the wider community of researchers in speech science, language, cognition and machine learning for which Edinburgh is renowned.
Address:
Informatics Forum
10 Crichton Street
Edinburgh
EH8 9AB
The Centre for Vision, Speech and Signal Processing (CVSSP) is one of the major research centres of the Faculty of Engineering and Physical Sciences of the University of Surrey. Its aim is to advance the state of the art in multimedia signal processing and computer vision, with a focus on image, video and audio applications. The research work in the Centre is structured into four main areas: Multimedia Signal Processing and Interpretation, Visual Media, Medical Imaging and Robot Vision. The Centre’s expertise and activities span multimedia applications (video coding and retrieval), digital broadcast production, speech and audio processing, picture quality assessment, biometric personal identity authentication, document analysis, medical imaging, automatic visual inspection, mobile robotics, remote sensing, cognitive vision, human-computer interfaces, and dynamic 3D object and environment modelling. The Centre, one of the largest in the UK, has about 100 members comprising academic and support staff, postdoctoral research fellows, visitors and PhD students. Its annual research income is in excess of 9.5m, with about 90 percent resourced by grants from EPSRC, EC and industry.
Address:
The University of Surrey,
Guildford,
Surrey,
GU2 7XH
Computational modelling of auditory and speech perception in humans and machines
Robustness in speech recognition
Large vocabulary speech recognition systems and their applications
An aspect of the group which makes it unique in the United Kingdom is the wide spectrum of research topics covered, from the psychology of hearing through to the engineering of large vocabulary speech recognition systems. It is our belief that studies at different points in this spectrum can and should be mutually beneficial.
Address:
Department of Computer Science
University of Sheffield
Regent Court
211 Portobello
Sheffield, S1 4DP
The Speech Research Group is part of the Machine Intelligence Laboratory. Its mission is to advance our knowledge of computer-based spoken language processing and develop effective algorithms for implementing applications. Its primary specialism is in large vocabulary speech transcription and related technologies. It also has active research interests in spoken dialogue systems, multimedia document retrieval, speech synthesis and machine learning.
The multi-disciplinary Speech Science Research Centre promotes both pure and applied research into speech and non-verbal communication in normal speakers and those with a variety of speech and language disorders. It focuses on instrumental analysis using sophisticated technology such as Electropalatography (EPG) , Electromagnetic Articulography (EMA) , Ultrasound, and other computerized equipment for assessing, treating and recording speech and other forms of communication. The Centre aims to become established as a leading centre for quantitative clinical phonetics.
UCL Speech Hearing and Phonetic Sciences is internationally recognised for its excellent research into the perception and production of speech. We combine basic research into the normal mechanisms of speech and hearing with applied research into problems caused by hearing impairment and by atypical perceptual and cognitive development. Our methodologies include behavioural experimentation, computational modelling, acoustic analysis and neuro-imaging. We provide scientific and technical expertise to a number of collaborative research projects at UCL and beyond.
There are several closely-linked areas involving speech, language and music that are covered within the Laboratory. For many years, we have done fundamental research into speech and language processing algorithms (e.g. speech recognition in noise, formulaic language modelling, language processing for speech synthesis) and development of applications of speech processing (e.g. call-routing, recognition of speech transmitted using VOIP, dysarthric speech). A recent application area of interest is distributed speech recognition (DSR), an emerging technology in which recognition is divided between a client and its server, and we have been active in defining the international DSR standard. We have developed methods of estimating speech information lost in transmission across networks and compensating for this loss in the recognition process.
Address:
School of Computing Sciences
University of East Anglia
Norwich
NR4 7TJ
Development and evaluation of new theory and computational paradigms for acoustic modelling, Development and evaluation of parsimonious models for robust speech recognition, inspired by linguistically and physically plausible models of speech production. Application to speech and language technology in education; speech technologies for children; approaches to regional accents. Integration of speech with gaze and gesture.
Address:
School of Electronic, Electrical and Systems Engineering
University of Birmingham
Edgbaston, Birmingham
B15 2TT
Telephone:
+44 (0) 121 414 3093
EMail:
m.j.russell@bham.ac.uk
Organisation Statement
UKSpeech is a non-profit making organisation run for the benefit of the UK and Ireland Speech Science and Speech Technology community. For more information contact admin@ukspeech.org.uk.
