| EPSRC Reference: |
GR/K54229/01 |
| Title: |
STATISTICAL TEXT ANALYSIS FOR SPEECH SYNTHESIS |
| Principal Investigator: |
Isard, Mr S |
| Other Investigators: |
|
| Researcher Co-Investigators: |
|
| Project Partners: |
|
| Department: |
Theoretical and Applied Linguistics |
| Organisation: |
University of Edinburgh |
| Scheme: |
Standard Research (Pre-FEC) |
| Starts: |
01 April 1996 |
Ends: |
30 June 1999 |
Value (£): |
171,152
|
| EPSRC Research Topic Classifications: |
| Human Communication in ICT |
|
|
| EPSRC Industrial Sector Classifications: |
|
| Related Grants: |
|
| Panel History: |
|
|
Summary on Grant Application Form |
|
Text-to-speech (TTS) systems take unrestricted text and convert it into speech. Current TTS systems generally produce good quality speech, but often make what seems like silly mistakes; emphasis is placed in the wrong place, the phrasing is un-natural and word are pronounced incorrectly. Many of these errors are due to problems with the text analysis part of the system, rather than with the speech synthesizer itself. The purpose of the proposed project is to use the recently developed techniques in statistical parsing and part of speech tagging to improve the performance of the text analysis. In particular, exploiting statistical properties of specific text domains, such as new articles or email messages, should improve applications intended for these domains.
|
|
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.ed.ac.uk |