| EPSRC Reference: |
GR/M93734/01 |
| Title: |
THE PROBABILISTIC UNION MODEL: A MODEL FOR PARTIALLY AND RANDOMLY CORRUPTED SPEECH |
| Principal Investigator: |
Ji, Professor M |
| Other Investigators: |
|
| Researcher Co-Investigators: |
|
| Project Partners: |
|
| Department: |
Computer Science |
| Organisation: |
Queen's University of Belfast |
| Scheme: |
Standard Research (Pre-FEC) |
| Starts: |
01 March 2000 |
Ends: |
30 June 2003 |
Value (£): |
110,853
|
| EPSRC Research Topic Classifications: |
| Human Communication in ICT |
|
|
| EPSRC Industrial Sector Classifications: |
| Creative Industries |
Information Technologies |
| No relevance to Underpinning Sectors |
|
|
| Related Grants: |
|
| Panel History: |
|
|
Summary on Grant Application Form |
|
This research deals with the problem of speech recognition subject to partial frequency and/or duration corruption. Partial corruption accounts for the effects of many real-world noises, including e.g. a shut door, a telephone ring, a channel tone or any type of frequency-limited or abrupt noise. The difficulty of the recognition task is tied to the degree of available information concerning the noise. In this research, we assume an absence of appropriate knowledge about the noise characteristics, i.e. the occurring time, frequency band and statistical distribution of the intensity. This lack of knowledge is often experienced in many practical applications, and causes particular difficulties for present techniques such as model adaptation/compensation, which require information about the noisy environments. We have recently developed a new statistical approach, the probabilistic union model, to tackle the above problem. Our initial study for speech recognition in unknown, time-varying frequency-limited noise has shown significant performance achievements for this new model. We now wish to continue this work by both deepening the theoretical study and exploring more applications. The main aim will be to develop new speech recognition techniques that can effectively cope with partial, unknown, time-varying 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.qub.ac.uk |