Methodology for the use of verbal proxies for dynamic vocabulary additions in speech interfaces

Abstract

An application ( ) utilizing a speech recognition interface ( ) employs the use of verbal proxies to accomplish dynamic vocabulary updates. One or more proxies used by the application ( ) are defined ( ) and added to the vocabulary ( ) of the speech recognition interface ( ). Upon the speech recognition interface ( ) receiving a speech signal ( ) representative of a command containing a defined proxy, the recognized speech is converted to text by the speech recognition interface ( ) to generate a text version of the recognized speech ( ). The application receives the text version of the recognized speech ( ) and processes it in accordance with the received command ( ). A parsing function ( ) of the application ( ) receives the text version of the recognized speech and determines what proxy routine(s) of the application to send the speech information to ( ). The identified proxy function ( ) of the application receives the text version of the recognized speech, together with externally provided target information, and links a textual target contained in the target information to the defined proxy ( ). The proxy function ( ) further generates an update instruction ( ) that causes the speech recognition interface to insert the selected text-based target ( ), provided by the proxy function, into the grammar ( ) of the speech recognition interface, thereby updating the vocabulary ( ) and the grammar ( ) of the speech recognition interface.