Windows Speech Recognition

Windows Speech Recognition is aprogram included with several versions ofMicrosoft Windows. It first appeared inWindows Vista and is a component of all subsequent Windows releases. It is part of the Ease of Access category of programs.

Windows Speech Recognition uses the microphone to process voice commands. Using voice commands, Speech Recognition allows the user to select items on the screen and type text without the need for akeyboard ormouse.

Description[]

Setup[]

Upon initial setup, the Speech Recognition setup wizard will prompt the user to select the type of microphone in use, and to read an example sentence aloud. The microphone must be plugged in prior to starting the program.

Controlling[]

When started, Speech Recognition is "Sleeping" and will not process commands. It must be turned on by saying "Start listening". The program will then change to a "Listening" state and will process other commands. It can be changed to the "Sleeping" state by saying "Stop listening".

When a text input box is highlighted, Speech Recognition can listen for words and type them into the input box. Speech Recognition uses a dictionary to interpret words it hears. However, the user can add custom terms to the dictionary through the program's settings.

When prompted to show adisambiguation of the screen's elements, Speech Recognition will ask the user to select a portion of the screen, and subsequently select a portion of this selection, repeatedly doing so until a precise input can be made on the screen.

When prompted toshow numbers, Speech Recognition will overlay a unique number on every selectable element on the screen. It will select the element corresponding to the number the user says.

Windows Speech Recognition makes a set ofsounds to indicate actions it will take. The sounds that play during these events can be changed in the Sound settings, found in theControl Panel.