Data processing: speech signal processing – linguistics – language – Speech signal processing – Recognition
Reexamination Certificate
2006-08-25
2009-11-10
Vo, Huyen X. (Department: 2626)
Data processing: speech signal processing, linguistics, language
Speech signal processing
Recognition
C704S244000, C704S243000
Reexamination Certificate
active
07617103
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.
REFERENCES:
patent: 6308155 (2001-10-01), Kingsbury et al.
patent: 6341264 (2002-01-01), Kuhn et al.
patent: 7219055 (2007-05-01), Lucke
patent: 2005/0021337 (2005-01-01), Kwon
Acero Alex
Deng Li
He Xiaodong
Yu Dong
Magee Theodore M.
Microsoft Corporation
Vo Huyen X.
Westman Champlin & Kelly P.A.
LandOfFree
Incrementally regulated discriminative margins in MCE... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Incrementally regulated discriminative margins in MCE..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Incrementally regulated discriminative margins in MCE... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-4086795