Selection of a voice recognition data base responsive to video data

• US 5,586,171 A
• Filed: 07/07/1994
• Issued: 12/17/1996
• Est. Priority Date: 07/07/1994
• Status: Expired due to Term

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Bell Atlantic Network Services, Inc. (Verizon Communications Inc.)
• Inventors: Hanle, John P., Young, David E., Cheston, Frank, McAllister, Alex
• Primary Examiner(s): Hofsass, Jeffery
• Assistant Examiner(s): PRESSON, THOMAS
• Application Number:
  US08/271,884
• Time in Patent Office: 894 Days
• Field of Search: 379/201, 379/207, 379/88, 379/67, 379/188, 379/189, 379/196, 379/198, 379/199, 340/825.3, 340/825.31, 340/825.33, 340/825.34, 340/825.35
• US Class Current: 379/88.02
• CPC Class Codes: G10L 15/25 using position of the lips, movement of the lips or face analysis
• CPC Class Codes: G10L 2015/228 of application context
• CPC Class Codes: H04Q 3/0029 Provisions for intelligent networking

Abstract

In a switching system for connecting a call between a calling station and a called station, a system and method of voice recognition using a concentrated or distributed multiplicity of voice recognition and other resources with a facility for selecting an initial resource on the calling station going off-hook by sensing an image of the calling party accessing a demographic database and a biometric database using common channel signaling and sensing biometric information regarding the caller, and selecting a prompt to be delivered to the caller from a multiplicity of preselected prompts, and reacting to a response by the caller with further addressing of database information to continue to select from the multiplicity of resources the most appropriate resource or resources in reaction to caller utterances. According to another feature the selection of resources is aided by optical means at the calling station delivering information regarding characteristics of the caller including lip movement to permit lip reading.

Claims

1. A switching system including interconnected switching offices and stations connected to at least certain of said switching offices and a Common Channel Signaling System (CCSS) for controlling the connection of a calling station to a called station through said switching system;

a plurality of speech recognition resources connected to said switching system;

a calling station having a handset and having means associated therewith responsive to said calling station going off-hook for sensing an image and outputting a video signal containing information representative of said detected image;

a database associated with said CCSS having stored therein data corresponding to pre-established image information;

comparing means for comparing selected portions of the information represented by said digital signal with corresponding information in said database containing said data corresponding to pre-established image information and providing a signal representative of the degree of match;

means responsive at least partially to said degree of match to select at least one of said resources and to connect a signal from said calling station to said selected resource; and

means associated with said plurality of resources for outputting a signal responsive to a spoken command inputted to said calling station.

2. A switching system according to claim 1 including:

stadia means mounted on said handset at a predetermined distance apart for detection by said image sensing means to establish a known distance and provide a reference for establishing other distances represented in the image signal outputted by said sensing means.

3. A switching system according to claim 2 wherein said stadia means comprise radiation means.

4. A switching system according to claim 3 wherein said radiation means are mounted on said handset in a manner to protrude from at least one surface thereof to provide visibility from multiple directions including a direction parallel to said surface.

5. A switching system according to claim 2 wherein said image sensing means includes focusing means arranged to focus on said stadia means.

6. A switching means according to claim 5 wherein said image sensing means includes aiming means arranged to aim said image sensing means at said stadia means.

7. A switching means according to claim 2 including:

means for sensing loss of a direct line of sight between said image sensing means and said stadia means and for initiating a trigger signal to cause delivery to the handset of an audio prompt advising the user to face the station.

8. A switching system according to claim 1 including:

a database associated with said CCSS having stored therein biometric information;

means for addressing said database and accessing information therein in response to a caller holding said handset off-hook and sensing biometric input;

means responsive to said accessed information to at least partially contribute to the selection of at least one of said resources and to connect a signal from said calling station to said selected resource.

9. A switching system according to claim 1 including audio response means for generating a plurality of predetermined audio responses, wherein said audio response means generates an audio response responsive to said signal responsive to said spoken command.

10. A switching system according to claim 9 wherein said audio response requests a further spoken command from said calling station and including means associated with said plurality of resources for outputting a signal responsive to outputs from at least a pair of said resources operating in parallel.

11. A switching system according to claim 1 wherein said handset has mounted thereon sensing means for sensing biometric parameters and generating signals responsive to the parameters sensed;

and

means for rendering the signal outputted by said plurality of resources at least partially responsive to said signals responsive to parameters sensed.

12. A switching system according to claim 1 including:

an operator station;

timing means;

means for initiating timing by said timing means at a pre-determined occurrence after said calling station goes off-hook;

means establishing a pre-determined time duration for timing by said timing means; and

means responsive to said timing means reaching said pre-determined time duration to cause connection of said calling station to said operator station.

13. A switching system according to claim 1 including:

a database associated with said CCSS having stored therein demographic information related to said stations connected to said switching stations;

means for addressing said database in response to a station going off-hook to access demographic information relating to said off-hook station;

means responsive to said accessed information to supply input to the selection of at least one of said resources and to connect a signal from said calling station to said selected resource for outputting a signal responsive to a spoken inputted command to said calling station.

14. A switching system according to claim 13 including audio response means for generating a plurality of predetermined audio responses, wherein said audio response means generates an audio response responsive to said signal responsive to said spoken command.

15. A switching system according to claim 14 wherein said audio response invites a further spoken command to said calling station, and including means associated with said plurality of resources for outputting a signal responsive to outputs from at least a pair of said resources.

16. A switching system including interconnected switching offices and stations connected to at least certain of said switching offices and a Common Channel Signaling System (CCSS) for controlling the connection of a calling station to a called station through said switching system;

a plurality of recognition resources connected to said switching system;

a calling station having a handset and having means associated therewith responsive to said calling station going off-hook for sensing an image and outputting a video signal containing information representative of said detected image;

a database associated with said CCSS having stored therein data corresponding to pre-established image information;

comparing means for comparing selected portions of the information represented by said digital signal with corresponding information in said database containing said data corresponding to pre-established image information and providing a signal representative of the degree of match;

means responsive at least partially to said degree of match to select at least one of said resources and to connect a signal from said calling station to said selected resource; and

means associated with said plurality of resources for outputting a signal responsive to a spoken command inputted to said calling station.

17. A switching system according to claim 16 including:

stadia means mounted on said handset at a predetermined distance apart for detection by said image sensing means to establish a known distance and provide a reference for establishing other distances represented in the image signal outputted by said sensing means.

18. A switching system according to claim 17 wherein said stadia means comprise radiation means.

19. A switching system according to claim 18 wherein said radiation means are mounted on said handset in a manner to protrude from at least one surface thereof to provide visibility from multiple directions including a direction parallel to said surface.

20. A switching system according to claim 17 wherein said image sensing means includes focusing means arranged to focus on said stadia means.

21. A switching system according to claim 20 wherein said image sensing means includes aiming means arranged to aim said image sensing means at said stadia means.

22. A switching means according to claim 17 including:

means for sensing loss of a direct line of sight between said image sensing means and said stadia means and for initiating a trigger signal to cause delivery to the handset of an audio prompt advising the user to face the station.

23. A switching system according to claim 16 including:

a database associated with said CCSS having stored therein biometric information;

means for addressing said database and accessing information therein in response to a caller holding said handset off-hook and sensing biometric input;

means responsive to said accessed information to at least partially contribute to the selection of at least one of said resources and to connect a signal from said calling station to said selected resource.

24. A switching system according to claim 16 including audio response means for generating a plurality of predetermined audio responses, wherein said audio response means generates an audio response responsive to said signal responsive to said spoken command.

25. A switching system according to claim 24 wherein said audio response requests a further spoken command from said calling station, and including means associated with said plurality of resources for outputting a signal responsive to outputs from at least a pair of said resources operating in parallel.

26. A switching system according to claim 16 wherein said handset has mounted thereon sensing means for sensing biometric parameters and generating signals responsive to the parameters sensed;

and

means for rendering the signal outputted by said plurality of resources at least partially responsive to said signals responsive to parameters sensed.

27. A switching system according to claim 16 including:

an operator station;

timing means;

means for initiating timing by said timing means at a pre-determined occurrence after said calling station goes off-hook;

means establishing a pre-determined time duration for timing by said timing means; and

means responsive to said timing means reaching said pre-determined time duration to cause connection of said calling station to said operator station.

28. A switching system according to claim 16 including:

a database associated with said CCSS having stored therein demographic information related to said stations connected to said switching stations;

means for addressing said database in response to a station going off-hook to access demographic information relating to said off-hook station;

means responsive to said accessed information to supply input to the selection of at least one of said resources and to connect a signal from said calling station to said selected resource for outputting a signal responsive to a spoken command inputted to said calling station.

29. A switching system according to claim 28 including audio response means for generating a plurality of predetermined audio responses, wherein said audio response means generates an audio response responsive to said signal responsive to said spoken command.

30. A switching system according to claim 29 wherein said audio response invites a further spoken command to said calling station, and including means associated with said plurality of resources for outputting a signal responsive to outputs from at least a pair of sensors.

31. In a switching system including interconnected switching offices and stations having handsets connected to at least certain of said switching offices, a Common Channel Signaling System (CCSS) for controlling the connection of a calling station to a called station through said switching system, and a plurality of recognition resources connected to said switching system;

a method comprising the steps of;

responsive to a calling station going off-hook, sensing an image in a field of view adjacent to said calling station and generating a video signal containing information representative of said detected image;

comparing said information from said digital signal with prestored data corresponding to pre-established image information, and providing a signal representative of the degree of match;

at least partially responsive to said degree of match selecting at least one of said resources and connecting a signal from said calling station to said selected resource;

responsive to a spoken command from said calling station outputting from said plurality of resources a signal representative thereof.

32. A method according to claim 31 including the steps of:

providing on said handset of said calling station stadia means mounted a pre-determined distance apart and detecting said stadia means by an image sensing means to establish a known distance and provide a reference for establishing other distances represented in the image signal outputted by said sensing means.

33. A method according to claim 32 including the step of providing radiation from said stadia means for detection by said image sensing means.

34. A method according to claim 33 including the step of providing said radiation from said stadia means in at least two mutually perpendicular planes over sectors of a least 270 degrees in each plane.

35. A method according to claim 32 including the step of focusing said image sensing means on said stadia means.

36. A method according to claim 32 including the step of aiming said image sensing means at said stadia means.

37. A method according to claim 32 including the steps of:

sensing loss of a direct line of sight between said image sensing means and said stadia means; and

delivering to the handset of said calling station an audio prompt advising the user to face the station.

38. A method according to claim 31 including the steps of:

storing in a database associated with said CCSS biometric information;

addressing said database and accessing biometric information therein in response to a caller holding said handset at said calling station off-hook; and

selecting at least one of said resources and connecting a signal from said calling station to said selected resource at least partially on the basis of said biometric information.

39. A method according to claim 31 including the steps of:

storing a plurality of pre-determined audio responses; and

delivering to said calling party one of said prestored audio responses in response to said spoken command.

40. A method according to claim 39 including the steps of:

requesting a further spoken command from said calling station; and

delivering to said calling party an audio signal responsive to outputs from at least a pair of said resources operating in parallel.

41. A method according to claim 31 including the steps of:

timing the call commencing with the off-hook condition; and

connecting said calling station to an operator station at the termination of a pre-determined interval.

42. A method according to claim 31 including the steps of:

establishing a database associated with said CCSS having stored therein demographic information related to said stations connected to said switching stations;

addressing said database in response to a station going off-hook to access demographic information relating to said off-hook station;

responsive to said accessed demographic information supplying input to the selection of at least one of said resources; and

connecting a signal from said calling station to said selected resource for outputting a signal responsive to a spoken command to said calling station.