EPSRC Reference: |
GR/K18962/01 |
Title: |
ROBUST SIGNAL PROCESSING AND RECOGNITION FOR OCCLUDED SPEECH |
Principal Investigator: |
Cooke, Professor M |
Other Investigators: |
|
Researcher Co-Investigators: |
|
Project Partners: |
|
Department: |
Computer Science |
Organisation: |
University of Sheffield |
Scheme: |
Standard Research (Pre-FEC) |
Starts: |
01 January 1995 |
Ends: |
31 December 1997 |
Value (£): |
109,617
|
EPSRC Research Topic Classifications: |
Digital Signal Processing |
Human Communication in ICT |
|
EPSRC Industrial Sector Classifications: |
|
Related Grants: |
|
Panel History: |
|
Summary on Grant Application Form |
This project aims to demonstrate robust automatic speech recognition (ASR) in arbitrary acoustic backgrounds. Current systems perform unreliably in moderate levels of background noise, levels which present listeners with little difficulty. Our recent work has modelled human auditory grouping principles in order to provide a general answer to the question of how best to deal with signal occlusion, and we have several solid demonstrations of SNR improvement for a wide variety of acoustic mixtures. The current project aims to apply that work to ASR. In the first stage, we will develop theoretical and algorithmic results to allow the training of a speech recogniser from an incomplete time-frequency description. This will provide a complete bottom-up path from occluded to recognised speech. The second phase of the project aims to provide a feedback route from recognised speech to the segregation process. One mechanism which we believe can bring both bottom-up (data-driven) and top-down (expectation-driven) factors to bear on speech segregation is a scheme using synchronised oscillations between neuronal groups. We intend to implement a computational model of this scheme in order to provide a robust pre-processor for ASA in noise.
|
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.shef.ac.uk |