11.0

Acoustic and Language Model Optimization

Vocabulary customization and proper correction of recognition errors both help Dragon recognize your

dictations more accurately. “Accuracy Tuning” is a functionality you can use to further “tune” your profile’s

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).

IMPORTANT

: If you have recently dictated in a very different sound environment, such as an airplane, you

should not let Dragon perform acoustic optimization.

The Accuracy Tuning process becomes available once you have performed enough dictation, correction and

training. Dragon will let you know once it has collected enough data for its automatic optimization.

The accuracy boost from Accuracy Tuning will depend on factors such as the amount and quality of the initial

training and optimization (if performed during profile creation), the initial accuracy you experienced, and the

amount and quality of text and audio data available for processing.

You can choose to schedule Accuracy Tuning to run periodically, at a time and frequency of your choice. You

can also launch it, as shown below.

Launching the Acoustic and/or Language Model Optimization

Step 1: Use the DragonBar’s Audio menu (or, in the Accuracy Center, use the link “Launch Accuracy Tuning

now”).