Details of Grant 

EPSRC Reference:	GR/M37219/01
Title:	DYNAMIC SEQUENTIAL SIMULATION METHODOLOGY WITH APPLICATION TO AUDIO, SPEECH AND COMMUNICATIONS
Principal Investigator:	FitzGerald, Professor W
Other Investigators:	Niranjan, Professor M Godsill, Professor S
Researcher Co-Investigators:
Project Partners:	A T & T Laboratories-Cambridge Ltd DSTL Air Systems Bedford Duke University
Department:	Engineering
Organisation:	University of Cambridge
Scheme:	Standard Research (Pre-FEC)
Starts:	01 January 1999	Ends:	30 June 1999	Value (£):	171,413
EPSRC Research Topic Classifications:	Digital Signal Processing
EPSRC Industrial Sector Classifications:	No relevance to Underpinning Sectors
Related Grants:
Panel History:
Summary on Grant Application Form
Our proposal will develop new methodology for the important problem of sequential ('on line') analysis of dynamic models, focusing on several key models which are of current importance in the fields of speech, audio, communications and tracking. The methodological developments will, however, be generic and we foresee wide applicability across many other areas of Science and Engineering where large quantities of data are presented in sequential fashion.The project takes as its starting point the state of the art in Bayesian sequential methods. These are simulation-based, using sampling-importance-re-sampling (SIR) and, in recent refinements, Markov Chain Monte Carlo (MCMC) to achieve propagation of probability distributions through time. We will address some short comings of these new methods, incorporating ideas from well-developed MCMC approaches to batch ('off-line') processing of time series to achieve sequential analysis of sophisticated, realistic models. Areas where we aim to advance current methods in particular include fixed-lag smoothing, models with non-dynamic hyper parameters, exploitation of analytic structure in models and the troublesome case of prior/data conflicts.The new methods will be applied to specific models in the areas of speech, audio, communications and tracking, allowing further refinement of the methods and quantitative comparison with others available
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.cam.ac.uk