As you correct misrecognitions, train the pronunciation of words, and perform General Training, you are creating new acoustic information that Dragon needs to improve your recognition accuracy. Dragon Medical 10 (10.1) stores this new acoustic information in a special data archive.
The Acoustic and Language Model Optimizer is a tool in Dragon that analyzes the new acoustic information, that is in the special data archive, and will improve your future dictation accuracy.
The Acoustic and Language Model Optimizer is a very resource intense process and may take up to three hours to complete. Therefore, you should schedule this tool to run at a time that you will not be using the computer.
To schedule the Acoustic and Language Model Optimizer open the Accuracy Center and select Schedule Acoustic and Language Model Optimizer to run later. This opens the Acoustic and Language Model Optimizer Scheduler Window.
In the Upper left corner you will see the User File(s).
Click File > New Task
This brings up the Microsoft Windows User Name and Password Dialog Box. This is because the Acoustic and Language Model Optimizer Scheduler is using the Microsoft Windows Scheduled Tasks.
Entering a valid Windows User Name and Password is required to schedule the Acoustic and Language Model Optimizer. If you do not enter the User Name and Password, you cannot schedule the Acoustic and Language Model Optimizer.
Also, if you enter an invalid User Name and Password the scheduler may not perform properly.
If you do not have a Windows User Name and Password established on your computer, you will have to create one in order to schedule the Acoustic and Language Model Optimizer.
In the Select Frequency Dialog Box everything is grayed out until you select a User Name. At the top of this window you have the option to Perform Acoustic Optimization and Perform Language Model Optimization.
In the User Information Section you can select or change the User Name or click the Multiple Users Button
Select the Dictation Source for this task.
Dragon can run the Acoustic Optimization on only one Dictation Source at a time.
Expand the Vocabulary Drop Down List and chose the vocabulary.
Dragon can run the Language Model Optimization on only one vocabulary at a time.
In the Select Frequency and Start Date and Time Section you have the options to schedule this task for:
• One Time Only
Select the Start Date and Start Time.
Remember, you want to schedule the task for a time that you will not be using your computer, and this process may take up to three hours to complete depending on how much data is in the Acoustic Archive.
Make sure the Enabled option is selected
At the top of the window you can see the status of the scheduled task.
This new task will automatically be saved when you close the Acoustic and Language Model Optimizer Scheduler.
Yes, the computer must be left on for this scheduled task to perform.