|Speech Recognition / Troubleshooting Speech Recognition|
When a user issues a verbal command to the Genie or responds to a question the Genie asks, Vocera attempts to process the utterance by finding a match in the recognition space. The recognition space has the following components:
A static grammar, which includes commands such as "Call" and "Broadcast" as well as possible responses such as "Yes" and "No", digits such as "One" and "Two", and so forth. The static grammar is installed by Vocera and cannot be changed by a customer.
A dynamic grammar, which includes all the spoken names a user can possibly utter. The dynamic grammar includes the names of users, groups, sites, locations, address book entries, and all their possible alternates, such as spellings of user names and the singular and plural names of groups.
Each site has its own dynamic grammar. It is completely determined by values that you enter in the database.
A personal grammar, which includes the buddies of an individual user, as well as any personal learned names, and learned commands.
Each user has his or her own personal grammar.
The recognition space varies according to the user issuing the command and the site the user is calling. That is, because each site has its own grammar, and each user has a personal grammar, the actual recognition space is likely to be slightly different for any individual making a call.