Google Voice Search now enables personalized voice recognition. If you opt into personalized recognition, Google will begin to associate the recordings of the words with a user's Google account. Google then automatically will use these words to build a speech model specifically for a particular user. This speech model enables Google to deliver greater recognition accuracy. Although subtle, accuracy improvements begin fairly quickly and will build over time.
The first time a user accesses Voice Search, that user will be presented with a dialog to turn on personalized recognition. Users can enable or disable personalized recognition at any time.
The personalized recognition functionality is currently available for English in the United States.
To enable it, a user must have Android 2.2 or higher, and download the latest version of the Voice Search app from Android Market.
