Although technically, voice recognition is part of biometric verification, it's primary application is to convert speech into commands and not principally for security or access control. Voice recognition has many advantages most notably allowing people to keep their eyes and hands free while "voicing instructions" to the computer. Quite often with voice recognition, the user is required to build instructional voice command sets. These command sets optimise speech recognition which in turn reduce the number of translational errors. Voice recognition is used in many professional fields including healthcare, legal, journal, publishing, etc., generally, anywhere requiring hands-free operation.
Dictation is a thing of the past. Doctors and lawyers can dictate minutes, notes, and proceedings directly into most Windows applications. Most voice recognition programs even support the capability to open files, pull down menus, close applications, change Windows, etc.
Voice recognition systems are generally PC based. They include a microphone, software and a digital processor card to interpret the voiced instructions. Some manufacturers have specialised vocabularies to optimise the performance by increasing the recognition accuracy. Other manufacturers systems are best suited to support single voice command statements and cannot interpret sentences. With most systems, however, each one must be "programmed" to recognise a user's voice pattern.