Method and apparatus for recognizing speech information based on prediction
US6598017B1 · kind B1 · utility
39Cited by
12References
77Claims
0Family size
Assignee
Inventors
Key dates
| Filing date | Jul 20, 1999 |
| Grant date | Jul 22, 2003 |
| Priority date | — |
| Expiry date | Jul 20, 2019 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG10L15/1815
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
An apparatus for recognizing sound information includes a sound recognition unit for recognizing sound information. A knowledge base stores knowledge concerning a type of data represented by the sound information. A prediction unit predicts the type of data represented by sound information to be subsequently recognized by checking the knowledge stored in the knowledge base. The sound recognition unit recognizes sound information to be subsequently recognized based on a prediction result obtained by the prediction unit. With this arrangement, the recognition accuracy is enhanced.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.