Method and apparatus of specifying and performing speech recognition operations
US7720683B1 · kind B1 · utility
732Cited by
11References
31Claims
0Family size
Assignee
Inventors
Key dates
| Filing date | Jun 10, 2004 |
| Grant date | May 18, 2010 |
| Priority date | — |
| Expiry date | Apr 9, 2028 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG10L2015/0631
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A speech recognition technique is described that has the dual benefits of not requiring collection of recordings for training while using computational resources that are cost-compatible with consumer electronic products. Methods are described for improving the recognition accuracy of a recognizer by developer interaction with a design tool that iterates the recognition data during development of a recognition set of utterances and that allows controlling and minimizing the computational resources required to implement the recognizer in hardware.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.