Details of Grant 

EPSRC Reference:	GR/R67958/01
Title:	ROPA : High Level Modelling and Interence for Audio Signals Using Bayesian Atomic Decompositions
Principal Investigator:	Godsill, Professor S
Other Investigators:
Researcher Co-Investigators:
Project Partners:
Department:	Engineering
Organisation:	University of Cambridge
Scheme:	ROPA
Starts:	01 February 2002	Ends:	31 January 2004	Value (£):	116,301
EPSRC Research Topic Classifications:	Digital Signal Processing
EPSRC Industrial Sector Classifications:	Creative Industries
Related Grants:
Panel History:
Summary on Grant Application Form
This project will explore new signal processing models appropriate for audio by means of Bayesian atomic decompositions. Such models will be constructed from overcomplete dictionaries of time-frequency/scale atoms as well as stochastic modelling of residuals. Structured hierarchical prior probability distributions will be developed specifically for audio signals (especially music) in order to model coefficient structure in time and frequency, along with hybrid Monte Carlo/deterministic Bayesian inference strategies for efficient implementation. We envisage that these new representations will fit naturally into high-level applications such as transcriptio source separation, segmentation and classification, and have the potential to improve their effectiveness dramatically.
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