Speech recognition device using statistical language model
US7698137B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Jul 29, 2008 |
| Grant date | Apr 13, 2010 |
| Priority date | — |
| Expiry date | Jul 29, 2028 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG10L15/183
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Embodiments of the present invention include a specific sentence generator for generating a piece of sentence data specific to an application from a grammar stored in a grammar storing unit and correction information stored in a correction information storing unit and then storing the piece of data in specific sentence storing unit, a topic shift unit for shifting a general topic stored in a general topic storing unit to a topic specific to an application on the basis of the piece of sentence data and then storing the topic in a shifted topic storing unit, a natural speech recognition unit for recognizing speech by dictation with a shifted topic and then storing the recognition result in a recognition result storing unit, a candidate sentence generator for generating candidate sentences from a grammar and then storing the sentences in a candidate sentence storing unit, and a matching unit for determining a final recognition result by matching candidate sentences with a recognition result.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.