Enhanced likelihood computation using regression in a speech recognition system
US6493667B1 · kind B1 · utility
Assignee
Inventors
Key dates
| Filing date | Aug 5, 1999 |
| Grant date | Dec 10, 2002 |
| Priority date | — |
| Expiry date | Aug 5, 2019 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG10L2015/085
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
In order to achieve low error rates in a speech recognition system, for example, in a system employing rank-based decoding, we discriminate the most confusable incorrect leaves from the correct leaf by lowering their ranks. That is, we increase the likelihood of the correct leaf of a frame, while decreasing the likelihoods of the confusable leaves. In order to do this, we use the auxiliary information from the prediction of the neighboring frames to augment the likelihood computation of the current frame. We then use the residual errors in the predictions of neighboring frames to discriminate between the correct (best) and incorrect leaves of a given frame. We present a new methodology that incorporates prediction error likelihoods into the overall likelihood computation to improve the rank position of the correct leaf.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.