| EPSRC Reference: |
GR/L59559/01 |
| Title: |
ROPA: MULTIPLE NEURAL NETWORK MODELS FOR LOW BIT-RATE SPEECH CODING |
| Principal Investigator: |
Tarassenko, Professor L |
| Other Investigators: |
|
| Researcher Co-Investigators: |
|
| Project Partners: |
|
| Department: |
Engineering Science |
| Organisation: |
University of Oxford |
| Scheme: |
ROPA |
| Starts: |
01 November 1997 |
Ends: |
31 October 1999 |
Value (£): |
70,923
|
| 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 |
|
The aim of this proposal is to utilise non-linear data compression techniques based on auto-associative neural networks for low bit rate speech coding. A high-dimensional representation (using sub-band or adaptive transform coding, for example) will be used as the input to a set of four-layer auto-associative networks. Multiple networks will be run in parallel, so that, for the different speech sounds, each network learns which components of the high-dimensional data (and their high-order correlations) are important for accurate reconstruction. The selection of the optimal model will take place within the coder, simply by computing the reconstruction error for each model. The intelligibility, quality and speaker recognisability of the proposed method will be assessed against LPC vocoders.
|
|
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.ox.ac.uk |