Incrementally regulated discriminative margins in MCE training for speech recognition
US7617103B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Aug 25, 2006 |
| Grant date | Nov 10, 2009 |
| Priority date | — |
| Expiry date | Jan 12, 2028 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG10L15/144
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A method and apparatus for training an acoustic model are disclosed. A training corpus is accessed and converted into an initial acoustic model. Scores are calculated for a correct class and competitive classes, respectively, for each token given the acoustic model. From this score a misclassification measure is calculated and then a loss function is calculated from the misclassification measure. The loss function also includes a margin value that varies over each iteration in the training. Based on the calculated loss function the acoustic model is updated, where the loss function with the margin value is minimized. This process repeats until such time as an empirical convergence is met.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.