Document creation through embedded speech recognition
US7006968B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Oct 11, 2001 |
| Grant date | Feb 28, 2006 |
| Priority date | — |
| Expiry date | Aug 14, 2023 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG10L15/26
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Audio data is captured, then filtered to extract text data and print commands. The audio data is captured by sensing the audio data, generating an analog audio data signal in response to the sensed audio data, and digitizing the analog audio data signal into captured audio data. The text data is converted to electronic text. The electronic text is accumulated in a text buffer. Audio data is captured and filtered to extract text data and print comments until a print command is extracted from the audio data. When a print command is extracted from the audio data, the accumulated electronic text is translated into a rendered document. The electronic text is either translated alone or with a form template. The rendered document is printed and the text buffer is purged.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.