Details of Grant 

EPSRC Reference:	GR/S63236/01
Title:	Robust Speaker Recognition in Noisy Conditions - A Feasibility Study
Principal Investigator:	Ji, Professor M
Other Investigators:	Hanna, Dr P Stewart, Dr DW Corr, Dr P
Researcher Co-Investigators:
Project Partners:	BlueChip Technologies Limited First Trust Bank Forensic Science Agency of Northern Irel Forensic Science Service Ltd
Department:	Computer Science
Organisation:	Queen's University of Belfast
Scheme:	Standard Research (Pre-FEC)
Starts:	01 February 2004	Ends:	31 January 2005	Value (£):	61,451
EPSRC Research Topic Classifications:	Human Communication in ICT
EPSRC Industrial Sector Classifications:	Communications
Related Grants:
Panel History:
Summary on Grant Application Form
This 60k feasibility study, conducted over 12 months by Queen's University Belfast, will investigate the problem of speaker recognition in noisy conditions, i.e.., using a noise-corrupted voice sample to identify or verify a person. Speaker recognition has a broad range of potential applications for crime prevention and detection, where a voice sample is left as the only or an additional source of evidence. Many existing speaker recognition systems work well only in quiet environments for speech recorded with little or no noise. In real-world environments, accurate speaker recognition remains problematic due to environmental and transmission-channel noise distortion. An effective solution to noise robustness is essential for crime related applications. This research aims to develop a new speaker recognition method that offers significantly improved noise robustness, while requiring no prior knowledge about the noise. The new method will be built upon our previous studies on noisy speech recognition. The method includes the characterisation of voice signals by using multiple feature streams, and the optimal selection of the least severely corrupted feature streams for recognition. The proposed study will be focused on application oriented experimentation/optimisation and a thorough investigation of the potential applications of this technology to crime prevention and detection through collaboration with a number of end-user bodies.
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.qub.ac.uk