Global speech user interface

Abstract

A global speech user interface (GSUI) comprises an input system to receive a user's spoken command, a feedback system along with a set of feedback overlays to give the user information on the progress of his spoken requests, a set of visual cues on the television screen to help the user understand what he can say, a help system, and a model for navigation among applications. The interface is extensible to make it easy to add new applications.

1 . A global speech user interface (GSUI) device, comprising:
 a processor device configured for performing speech recognition to transcribe spoken commands for use in navigating among one or more applications hosted on a communications system;   said processor device configured for displaying a set of visual cues to guide a user in issuing spoken commands to navigate among the one or more applications, said visual cues comprising a set of feedback overlays, each of which provides information about a problem that said communications system is experiencing;   said processor device further configured for, responsive to said communications system encountering a problem recognizing the spoken commands, providing a list including a plurality of possible recognition matches,   wherein the list including the plurality of possible recognition matches is provided in response to satisfying a particular recognition feedback condition.   
     
     
         2 . The interface device of  claim 1 , wherein said visual cues further comprise a help menu overlay that shows help services available, the help menu overlay providing any of the following services:
 training and tutorials on how to use the communications system;   help with specific speech-activated applications;   user account management; or   user settings and preferences for the communications system.   
     
     
         3 . The interface device of  claim 1 , wherein said visual cues further comprise a help menu overlay that shows help services available, the help menu overlay providing a context-sensitive list of frequently used speech activated commands. 
     
     
         4 . The interface device of  claim 1 , wherein said visual cues further comprise a main menu overlay that shows a list of services available to the user, each of said services being accessible by spoken command. 
     
     
         5 . The interface device of  claim 1 , wherein said visual cues further comprise a set of immediate speech feedback overlays, wherein each of the immediate speech feedback overlays provides non-textual information about a state of the communications system, the state being any of:
 listening to the user's spoken command; or   speech recognition processing.   
     
     
         6 . The interface device of  claim 1 , further comprising:
 a user personalization and identification mechanism, wherein said user personalization and identification mechanism presents any of different custom interfaces or personalized content for different respective users.   
     
     
         7 . The interface device of  claim 6 , wherein said user personalization and identification mechanism identifies respective users by voice. 
     
     
         8 . The interface device of  claim 7 , wherein said user personalization and identification mechanism includes a mechanism for training said communications system to identify respective users by voice. 
     
     
         9 . The interface device of  claim 1 , wherein:
 said processor device is configured for initiating, via spoken command, an automatic scan search for content comprising one or more programs pursuant to a search category.   
     
     
         10 . The interface device of  claim 9 , wherein each matching program remains on screen for a predetermined period of time before advancing to next matching program. 
     
     
         11 . The interface device of  claim 1 , wherein:
 said processor device is configured for, via spoken command, performing any of:
 adding content to categories; 
 editing content in categories; or 
 deleting content from categories. 
   
     
     
         12 . The interface device of  claim 1 , wherein:
 said processor device is configured for, via spoken command, filtering groups of content by specific attributes.   
     
     
         13 . The interface device of  claim 1 , wherein said processor device is configured for execution of an interactive program guide, said interactive program guide configured for any of:
 responsive to a spoken command, sorting content by category;   responsive to a spoken command, setting parental controls, wherein which children are blocked from accessing controlled channels or content;   responsive to a spoken command, setting reminders for content to play in the future;   responsive to a spoken command, searching content based on a specific criteria;   processing pay per view purchases; or   responsive to a spoken command, any of accessing and upgrading premium content services.   
     
     
         14 . The interface device of  claim 1 , wherein said processor device is configured for, based upon voice identification, any of:
 targeting one or more advertisements contained in an application screen to a user;   targeting content recommendations to a user;   delivering personalized information to a user; or   automatically configuring a user's interface preferences.   
     
     
         15 . The interface device of  claim 1 , wherein said processor device is configured for, based upon voice identification, varying display of content comprising any of:
 displaying advertisements personalized to a specific speaker;   displaying programming recommendations personalized to a specific speaker;   displaying video-on-demand purchase recommendations personalized to a specific speaker;   expediting an on-screen purchase transaction based upon recognition of a specific speaker;   displaying an interface and content personalized to a specific speaker;   automatically configuring the display or user interface according to preferences of a specific speaker; or   implementing a designated scheme for parental control of content by automatically blocking or allowing content according to identity of a specific speaker.   
     
     
         16 . The interface device of  claim 1 , wherein the problem recognizing the spoken commands satisfies a particular recognition feedback condition of a plurality of recognition feedback conditions that correspond to amounts of information about an utterance. 
     
     
         17 . The interface device of  claim 1 , wherein the problem recognizing the spoken commands includes a latency in the communications system. 
     
     
         18 . The interface device of  claim 1 , wherein the problem recognizing the spoken commands is encountered by a speech engine in said communications system. 
     
     
         19 . A method for use with a global speech user interface (GSUI) device, comprising:
 performing, by a processor device, speech recognition to transcribe spoken commands for use in navigating among one or more applications hosted on a communications system;   displaying, by the processor device, a set of visual cues to guide a user in issuing spoken commands to navigate among the one or more applications, said visual cues comprising a set of feedback overlays, each of which provides information about a problem that said communications system is experiencing;   responsive to said communications system encountering a problem recognizing the spoken commands, and in response to satisfying a particular recognition feedback condition, providing, by the processor device, a list including a plurality of possible recognition matches.   
     
     
         20 . The method of  claim 19 , wherein said visual cues further comprise a help menu overlay that shows help services available, the help menu overlay providing any of the following services:
 training and tutorials on how to use the communications system;   help with specific speech-activated applications;   user account management; or   user settings and preferences for the communications system.   
     
     
         21 . The method of  claim 19 , wherein said visual cues further comprise a help menu overlay that shows help services available, the help menu overlay providing a context-sensitive list of frequently used speech activated commands. 
     
     
         22 . The method of  claim 19 , wherein said visual cues further comprise a main menu overlay that shows a list of services available to the user, each of said services being accessible by spoken command. 
     
     
         23 . The method of  claim 19 , wherein said visual cues further comprise a set of immediate speech feedback overlays, wherein each of the immediate speech feedback overlays provides non-textual information about a state of the communications system, the state being any of:
 listening to the user's spoken command; or   speech recognition processing.   
     
     
         24 . The method of  claim 19 , further comprising:
 presenting any of different custom interfaces or personalized content for different respective users.   
     
     
         25 . The method of  claim 24 , wherein presenting of different custom interfaces or personalized content is based on identifying respective users by voice. 
     
     
         26 . The method of  claim 25 , further comprising training said communications system to identify respective users by voice. 
     
     
         27 . The method of  claim 19 , wherein:
 initiating via spoken command, by the processor device, an automatic scan search for content comprising one or more programs pursuant to a search category.   
     
     
         28 . The method of  claim 27 , wherein each matching program remains on screen for a predetermined period of time before advancing to next matching program. 
     
     
         29 . The method of  claim 19 , wherein:
 performing via spoken command, by the processor device, any of:
 adding content to categories; 
 editing content in categories; or 
 deleting content from categories. 
   
     
     
         30 . The method of  claim 19 , further comprising:
 filtering via spoken command, by the processor device, groups of content by specific attributes.   
     
     
         31 . The method of  claim 19 , further comprising performing, by an interactive program guide, any of:
 responsive to a spoken command, sorting content by category;   responsive to a spoken command, setting parental controls, wherein which children are blocked from accessing controlled channels or content;   responsive to a spoken command, setting reminders for content to play in the future;   responsive to a spoken command, searching content based on a specific criteria;   processing pay per view purchases; or   responsive to a spoken command, any of accessing and upgrading premium content services.   
     
     
         32 . The method of  claim 19 , further comprising performing, by the processor device and based upon voice identification, any of:
 targeting one or more advertisements contained in an application screen to a user;   targeting content recommendations to a user;   delivering personalized information to a user; or   automatically configuring a user's interface preferences.   
     
     
         33 . The method of  claim 19 , further comprising performing, by the processor device and based upon voice identification, any of:
 displaying advertisements personalized to a specific speaker;   displaying programming recommendations personalized to a specific speaker;   displaying video-on-demand purchase recommendations personalized to a specific speaker;   expediting an on-screen purchase transaction based upon recognition of a specific speaker;   displaying an interface and content personalized to a specific speaker;   automatically configuring the display or user interface according to preferences of a specific speaker; or   implementing a designated scheme for parental control of content by automatically blocking or allowing content according to identity of a specific speaker.   
     
     
         34 . The method of  claim 19 , wherein the problem recognizing the spoken commands satisfies a particular recognition feedback condition of a plurality of recognition feedback conditions that correspond to amounts of information about an utterance. 
     
     
         35 . The method of  claim 19 , wherein the problem recognizing the spoken commands includes a latency in the communications system. 
     
     
         36 . The method of  claim 19 , wherein the problem recognizing the spoken commands is encountered by a speech engine in said communications system.