Back to results
US 2010/0161330 A1Published application
Speech models generated using competitive training, asymmetric training, and data boosting
AssigneeMicrosoft Corporation
InventorsXiaodong He, Jian Wu
Life of this patent
Estimating the term…
Abstract
Speech models are trained using one or more of three different training systems. They include competitive training which reduces a distance between a recognized result and a true result, data boosting which divides and weights training data, and asymmetric training which trains different model components differently.
Claims8
A method of training a speech model, comprising:
- obtaining model parameters for the speech model;
- processing a known speech input using the speech model with the model parameters to generate a process result;
- calculating a distance between a true result and the process result, given the model parameters and the known speech input;
- and
- modifying the model parameters to reduce the distance between the true result and the process result, to obtain a modified model.
2 more elements
Dependencies are inferred from the claim text.