| 摘要 |
A voice recognition system with a graphical user interface (GUI) is provided by the present invention for visually prompting a user for expected inputs that the user can choose to speak at designated points in a dialog in order to improve the overall accuracy of the voice recognition system. By reading the GUI window, the user can know what the recognizable grammar and vocabulary are for spoken input at any moment in the dialog. The GUI and voice interface can be built from a single dictionary and grammar specification. Prompts that represent non-terminal tokens in the grammar are replaced with one of a set of other prompts in the grammar in response to spoken input. The GUI may further comprise pull-down menus as well as separate windows that open and close in response to user input. The system may also verbally prompt the user to provide certain spoken input. <IMAGE> |
