10.0

Acoustic and Language Model Optimization

Proper correction and Vocabulary customization both help Dragon recognize your speech more accurately.

Acoustic and Language Modeling Optimization is a functionality you can use to further “tune” the accuracy for

your specific usage:

• It refines your User profile using the latest acoustic data archived from any corrections and acoustic

training you performed.

• It uses text extracted from your previous dictations to add frequent word sequences to the Language

Model (Dragon’s statistical information that predicts which words are most likely to occur when you

dictate).

This “Accuracy Tuning” can take a while, depending on your computer’s resources and on the amount of data

accumulated. (Before running it, Dragon automatically backs up your User profile.)

It becomes available once you have performed enough dictation, correction and training. Depending on how

many hours of dictation you typically do, you might run it after a few weeks of using Dragon and then about

once a month.

The accuracy boost will depend on factors such as the amount and quality of the initial training and optimization (if

performed during profile creation, the initial accuracy experienced, and the amount and quality of text and audio

data available for processing.)

Note: If you have recently dictated in a very different sound environment, such as an airplane, you should not

let Dragon perform acoustic optimization.

Launching the Acoustic and/or Language Model Optimization

Step 1: In the Accuracy Center, use the link “Run the Acoustic and Language Model Optimizer.”