Speech recognition method using confidence measure evaluation
US6421640B1 · kind B1 · utility
Assignee
Inventors
Key dates
| Filing date | Sep 13, 1999 |
| Grant date | Jul 16, 2002 |
| Priority date | — |
| Expiry date | Sep 13, 2019 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG10L15/10
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
The invention relates to a method of automatically recognizing speech utterances, in which a recognition result is evaluated by means of a first confidence measure and a plurality of second confidence measures determined for a recognition result is automatically combined for determining the first confidence measure. To reduce the resultant error rate in the assessment of the correctness of a recognition result, the method is characterized in that the determination of the parameters weighting the combination of the second confidence measures is based on a minimization of a cross-entropy-error measure. A further improvement is achieved by means of a post-processing operation based on the maximization of the Gardner-Derrida error function.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.