User guide

Dragon 12 Installation and User Guide
you read something incorrectly. The computer either ignores the mistake or positions the
yellow arrow at the beginning of the text for you to reread it.
The progress bar shows how much text is left to dictate.
Note: During training, dictating punctuation is not necessary.
6. When you’ve read enough, the Training wizard displays a congratulations message. Click
OK and Dragon starts adapting to your voice.
Proceed to Adapting to your writing style, scheduling tuning.
Adapting to your writing style and scheduling
tuning
After it adapts to your voice, Dragon’s Accuracy wizard appears and prompts you to first
adapt Dragon to your writing style, then schedule regular Acoustic and Language Model tun-
ing, and optionally schedule Data Collection.
Adapting to your writing style (Let Dragon search for words and
add them now)
Dragon can analyze your writing style to increase your overall recognition accuracy. This tool
scans documents in your My Documents directory—Microsoft Word, Corel WordPerfect,
text files, html files, and rich text files (.rtf).
Adapting to your writing style can add 5 to 30 minutes to user training. Close all other pro-
grams when you run this step.
Note:
Though we recommend that you run this part of the New User Wizard, if you plan to skip
this step, select Skip this step rather than Cancel.
1. In the Let Dragon search for words and add them now page of the Accuracy wizard, to have
Dragon search for words and phrases you use in your email messages, select the Sent E-
mails check box. To have Dragon search your word processing and text files, select the My
Documents check box.
2. Click Start to initiate the search for words. While scanning your files, the dialog box dis-
plays the process’s status. When Dragon finishes searching, it displays a message telling
you to click Next to continue.
Let Dragon automatically improve your accuracy
After it adapts to your writing style, the Accuracy wizard gives you the option of setting up a
schedule to automatically run Acoustic and Language Model tuning processes:
41