SPHEAR TMR Network Partners

6.1 Sheffield

Speech and Hearing Research Group, Department of Computer Science, University of Sheffield, GB.

6.1.1 Experience and competence

The group is concerned with computational modelling of auditory and speech perception, in humans and machines. It was founded in 1986 & has been funded by the UK Alvey programme, the UK SERC Image Interpretation Initiative, British Telecom, DRA Malvern, the Nuffield Foundation, the UK Engineering and Physical Science Research Council, the EU Human Capital and Mobility Programme, The Royal Society, the Royal Academy of Engineering and ATR Kyoto. Three grants are current: the ESPRIT LTR projects SPRACH (ref. 20077) and THISL (ref 23495) and an EPSRC grant for Occluded Speech Recognition (GR/K18962).

6.1.2 Role in the project

Dr Phil Green of Sheffield acted as coordinator for the HCM-SPHERE network and is proposed as coordinator for SPHEAR (?8). Sheffield's main technical contributions to SPHEAR are in task 2.5 (the neuronal oscillator work, explained in ?4.2.1), missing data recognition (task 3.2, ?4.2.2) and near-speech recognition (task 3.6, ?4.2.2). Sheffield is also involved in the application work of theme 4 (tasks 4.3 and 4.4). Sheffield is supplying the ShATR database which will be used for several tasks in themes 1 and 2.

6.1.3 Research linkages

As coordinating site, Sheffield established good relationships with all SPHERE labs. Closest collaborations in SPHEAR are with Grenoble, Keele, Ericsson and IDIAP. Sheffield already works with IDIAP on the ESPRIT projects listed above.

6.1.4 Principal research personnel, expertise and involvement

Dr. Guy Brown, B.Sc. (CNAA), Ph.D. (Sheffield), Lecturer in Computer Science: expertise in auditory and speech perception, computational auditory scene analysis. Involvement 6 man-months.
Dr. Martin Cooke, B.Sc. (Manchester), Ph.D. (Sheffield), Reader in Computer Science: expertise in auditory and speech perception, computational auditory scene analysis. Involvement 6 man-months.
Dr. Phil Green, B.Sc. (Reading), Ph.D. (Keele), Reader in Computer Science: expertise in speech processing, automatic speech recognition. Involvement 9 man-months (project coordination), 6 man-months (research).

6.1.5 Recent publications

MP Cooke and GJ Brown (1994), 'Separating Simultaneous Sound Sources: Issues, Challenges and Models', in 'Fundamentals of Speech Synthesis and Speech Recognition', ed. E. Keller, John Wiley & Sons, p295-312.
PD Green, MP Cooke and MD Crawford (1995), 'Auditory Scene Analysis and HMM-Recognition of Speech in Noise, proc IEEE international conference on Acoustics, Speech and Signal Processing (ICASSP-95), Detroit, p401-404.