Unsupervised speech model adaptation using reliable information among N-best strings
US6205426A · kind A · utility
37Cited by
5References
26Claims
0Family size
Assignee
Inventors
Key dates
| Filing date | Jan 25, 1999 |
| Grant date | Mar 20, 2001 |
| Priority date | — |
| Expiry date | Jan 25, 2019 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG10L15/065
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
The system performs unsupervised speech model adaptation using the recognizer to generate the N-best solutions for an input utterance. Each of these N-best solutions is tested by a reliable information extraction process. Reliable information is extracted by a weighting technique based on likelihood scores generated by the recognizer, or by a non-linear thresholding function. The system may be used in a single pass implementation or iteratively in a multi-pass implementation.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.