Voice activated communication system and program guide

• US 6,654,721 B2
• Filed: 08/20/2001
• Issued: 11/25/2003
• Est. Priority Date: 12/31/1996
• Status: Expired due to Term

• Current Assignee: Synamedia Limited
• Original Assignee: News Datacom Ltd (Cisco Systems, Inc.)
• Inventors: Handelman, Doron
• Primary Examiner(s): Smits, Talivaldis Ivars
• Assistant Examiner(s): Azad, Abul K.
• Application Number:
  US09/933,097
• Publication Number:
  US 20020052746A1
• Time in Patent Office: 827 Days
• Field of Search: 704/270, 704/275, 704/271, 704/272, 704/276, 704/273, 725/38, 725/39, 382/181, 382/219, 382/229, 382/115
• US Class Current: 704/270
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: H04N 21/42203 sound input device, e.g. microphone
• CPC Class Codes: H04N 21/4223 Cameras H04N23/00 takes precedence
• CPC Class Codes: H04N 21/4415 using biometric characteristics of the user, e.g. by voice recognition or fingerprint scanning cryptography using biological data H04L9/3231; authentication in networks using biometric H04L63/0861
• CPC Class Codes: H04N 21/482 End-user interface for program selection broadcast systems using EPGs H04H60/72
• CPC Class Codes: H04N 7/163 by receiver means only

Abstract

A subscriber unit for use with a program guide selection system is described. The program guide selection system provides program guide information which is communicated over a communication network and includes operating characteristics of a communication system and selection codes which are associated with the operating characteristics of the communication system. The subscriber unit includes: a receiver for receiving the program guide information and the selection codes associated with the operating characteristics, a display for displaying the program guide information and the selection codes to a subscriber, a microphone which is employed by the subscriber, when the subscriber identifies on the display a selection code which is associated with a requested one of the operating characteristics, to orally input a voice expression which includes the selection code, and a speech recognition unit which is coupled to the microphone and is operative to enable selection of the requested one of the operating characteristics in response to the voice expression.

Claims

1. A program guide selection system comprising:

a communication network for communicating program guide information which includes operating characteristics of a communication system and selection codes associated with the operating characteristics of the communication system; and

a multiplicity of subscriber units, each including;

a receiver for receiving the program guide information and the selection codes associated with the operating characteristics;

a microphone employed by a subscriber for oral input of a selection code, the selection code being associated with a requested one of the operating characteristics of the communication system;

a camera operative to take a picture of the subscriber when located in a field of view of the camera;

a processor operative to associate speech characteristics of each of a multiplicity of speakers with images of each of the multiplicity of speakers;

an image processor operatively associated with the camera and the processor and operative to compare the picture of the subscriber to at least one of the images of each of the multiplicity of speakers and to determine whether the picture of the subscriber is substantially similar to an image of a speaker; and

a speech recognition unit operatively associated with the microphone and the processor and customized to respond to the selection code inputted orally by the subscriber and to enable selection of the requested one of the operating characteristics of the communication system associated with the selection code upon a determination that the picture of the subscriber is substantially similar to the image of the speaker, and that speech characteristics of the subscriber substantially match speech characteristics associated with the speaker.

2. The system according to claim 1 and wherein each of said selection codes includes at least one of the following:

a letter character;

a number character; and

a combination of letter and number characters.

3. A subscriber unit for use with a program guide selection system in which program guide information, which includes operating characteristics of a communication system, is communicated over a communication network, the subscriber unit comprising:

a receiver for receiving the program guide information and the operating characteristics of the communication system;

a microphone employed by a subscriber for oral input of a selection code, the selection code being associated with a requested one of the operating characteristics of the communication system;

a camera operative to take a picture of the subscriber when located in a field of view of the camera;

a processor operative to associate speech characteristics of each of a multiplicity of speakers with images of each of the multiplicity of speakers;

an image processor operatively associated with the camera and the processor and operative to compare the picture of the subscriber to at least one of the images of each of the multiplicity of speakers and to determine whether the picture of the subscriber is substantially similar to an image of a speaker; and

a speech recognition unit operatively associated with the microphone and the processor and customized to respond to the selection code inputted orally by the subscriber and to enable selection of the requested one of the operating characteristics of the communication system associated with the selection code upon a determination that the picture of the subscriber is substantially similar to the image of the speaker, and that speech characteristics of the subscriber substantially match speech characteristics associated with the speaker.

4. Apparatus according to claim 3 and also comprising a memory which communicates with at least one of the following:

said processor;

said speech recognition unit; and

said image processor, wherein

said memory is operative to store at least one of the following;

said speech characteristics of each of the multiplicity of speakers; and

said images of each of the multiplicity of speakers.

5. Apparatus according to claim 4 and wherein:

said memory comprises a removable external memory module;

said subscriber unit includes an external memory reader; and

said removable external memory module, when placed in operative association with said external memory reader, is operative to communicate, via said external memory reader, with at least one of the following;

said processor;

said

speech recognition unit; and

said image processor.

6. Apparatus according to claim 4 and also comprising a compressor/decompressor operative to compress at least one of:

said speech characteristics of each of the multiplicity of speakers; and

said images of each of said multiplicity of speakers, prior to storage in said memory,

and to decompress at least one of;

said speech characteristics of each of the multiplicity of speakers; and

said images of each of the multiplicity of speakers, upon retrieval from said memory.

7. Apparatus according to claim 3 and wherein:

said speech recognition unit comprises an external removable speech recognition module;

said subscriber unit also includes an interface unit; and

said external removable speech recognition module, when placed in operative association with said interface unit, is operative to enable selection of said requested one of the operating characteristics via said interface unit.

8. Apparatus according to claim 3 and also comprising an on-screen-display (OSD) unit operative to generate on-screen messages for display on a display in response to instructions provided by at least one of the following:

said speech recognition unit; and

said processor.

9. Apparatus according to claim 3 and also comprising a decrypter operative to decrypt encrypted incoming information in response to an authorization signal provided by at least one of the following:

said speech recognition unit; and

said processor.

10. Apparatus according to claim 3 and wherein:

said program guide information also comprises selection codes which are associated with the operating characteristics of the communication system;

said receiver is operative to receive said selection codes and to provide said selection codes to a display; and

the selection code, inputted orally by the subscriber, is selected from among said selection codes.

11. Apparatus according to claim 3 and also comprising a memory for storing at least one of:

selection codes which enable selections from the operating characteristics;

the speech characteristics of each of the multiplicity of speakers; and

the images of each of the multiplicity of speakers, wherein

the processor is operative to associate the selection codes with the operating characteristics, and

the selection code, inputted orally by the subscriber, is selected from among said selection codes.

12. Apparatus according to claim 3 and wherein said requested one of the operating characteristics comprises at least one of the following:

a program selection;

a system configuration;

a parental control parameter;

a message;

program guide scheduling; and

a selection of a channel.

13. A voice selection method for a user to select a requested one of operating characteristics of a program guide selection communication system from among a plurality of operating characteristics of the system which are displayed on a display, the method comprising:

providing a speech recognition unit which is operative to respond to speech from a multiplicity of speakers;

storing speech characteristics of each of the multiplicity of speakers;

associating the speech characteristics of each of the multiplicity of speakers with images of each of the multiplicity of speakers;

providing a camera which is operative to take a picture of the user when located in a field of view of the camera;

comparing the picture of the user to at least one of the images of the multiplicity of speakers;

determining that the picture of the user is substantially similar to an image of a speaker; and

executing a voice command, when the voice command is provided by the user and is associated with the requested one of operating characteristics, in response to said determining step and in accordance with a determination that speech characteristics of the user substantially match speech characteristics associated with the speaker.

14. The method according to claim 13 and wherein said executing step includes:

detecting the voice command provided by the user;

verifying that the voice command is a legitimate command associated with a selection of the requested one of operating characteristics; and

selecting said requested one of operating characteristics in response to said verifying step.

15. The method according to claim 13 and wherein said requested one of operating characteristics comprises at least one of the following:

a program selection;

a system configuration;

a parental control parameter;

a message;

program guide scheduling; and

a selection of a channel.

16. A voice selection method for enabling a user to select a requested one of operating characteristics of a program guide selection communication system from among a plurality of operating characteristics of the system which are displayed on a display, the method comprising:

receiving the plurality of operating characteristics;

associating the plurality of operating characteristics with selection codes which enable selections from the plurality of operating characteristics;

displaying the plurality of operating characteristics and the selection codes associated therewith;

storing speech characteristics of each of a multiplicity of speakers, and images of each of the multiplicity of speakers;

associating the speech characteristics of each of the multiplicity of speakers with the images of each of the multiplicity of speakers;

taking a picture of the user when located in a field of view of a camera;

identifying, on the display, a requested selection code which corresponds to the requested one of operating characteristics;

accepting, at a microphone, an oral input of a voice expression; and

selecting said requested one of operating characteristics associated with the selection code in response to coexistence of the following;

a determination that the picture of the user is substantially similar to an image of one of the multiplicity of speakers;

a determination that speech characteristics associated with said oral input of the voice expression substantially include an oral input of the requested selection code; and

a determination that the speech characteristics associated with the oral input of said voice expression substantially match the speech characteristics associated with the user.

17. The method according to claim 16 and wherein each of said selection codes includes at least one of the following:

a letter character;

a number character; and

a combination of letter and number characters.

18. The method according to claim 16 and wherein each of said selection codes includes at least one of the following:

a word;

a phrase; and

a sentence.

19. A subscriber unit for use with a program guide selection system in which program guide information, which includes operating characteristics of a communication system, is communicated over a communication network, the subscriber unit comprising:

receiving means for receiving the program guide information and the operating characteristics of the communication system;

means, to be employed by a subscriber, for oral input of a selection code, the selection code being associated with a requested one of the operating characteristics of the communication system;

means for taking a picture of the subscriber when located in a field of view of the camera;

processing means for associating speech characteristics of each of a multiplicity of speakers with images of each of the multiplicity of speakers;

comparing means for comparing the picture of the subscriber to at least one of the images of each of the multiplicity of speakers and for determining whether the picture of the subscriber is substantially similar to an image of a speaker; and

speech responsive means for responding to the selection code inputted orally by the subscriber and for enabling selection of the requested one of the operating characteristics of the communication system associated with the selection code upon a determination that the picture of the subscriber is substantially similar to the image of the speaker, and that speech characteristics of the subscriber substantially match speech characteristics associated with the speaker.

20. Apparatus according to claim 19 and also comprising storage means for storing at least one of the following:

said speech characteristics of each of the multiplicity of speakers; and

said images of each of the multiplicity of speakers.

21. Apparatus according to claim 20 and wherein:

said storage means comprise removable external storage means;

said subscriber unit includes access means for accessing said removable external storage means; and

said removable external storage means, when placed in operative association with said access means, are operative to communicate, via said access means, with at least one of the following;

said processing means;

said speech responsive means; and

said comparing means.

22. Apparatus according to claim 20 and also comprising compressing/decompressing means for compressing at least one of:

said speech characteristics of each of the multiplicity of speakers; and

said images of each of said multiplicity of speakers, prior to storage in said storage means,

and for decompressing at least one of;

said speech characteristics of each of the multiplicity of speakers; and

said images of each of the multiplicity of speakers, upon retrieval from said storage means.

23. Apparatus according to claim 19 and wherein:

said speech responsive means comprise external removable speech responsive means;

said subscriber unit also includes interfacing means for accessing said external removable speech responsive means; and

said external removable speech responsive means, when placed in operative association with said interfacing means, are operative to enable selection of said requested one of the operating characteristics via said interfacing means.

24. Apparatus according to claim 19 and also comprising on-screen displaying means for generating on-screen messages for display on a display in response to instructions provided by at least one of the following:

said speech responsive means; and

said processing means.

25. Apparatus according to claim 19 and also comprising decrypting means for decrypting encrypted incoming information in response to an authorization signal provided by at least one of the following:

said speech responsive means; and

said processing means.

26. Apparatus according to claim 19 and wherein:

said program guide information also comprises selection codes which are associated with the operating characteristics of the communication system;

said receiving means receive said selection codes and provide said selection codes to a display; and

the selection code, inputted orally by the subscriber, is selected from among said selection codes.

27. Apparatus according to claim 19 and also comprising storage means for storing at least one of:

selection codes which enable selections from the operating characteristics;

the speech characteristics of each of the multiplicity of speakers; and

the images of each of the multiplicity of speakers, wherein

the processing means associate the selection codes with the operating characteristics, and

the selection code, inputted orally by the subscriber, is selected from among said selection codes.

28. A subscriber unit for use with a program guide selection system in which program guide information, which includes operating characteristics of a communication system, is communicated over a communication network, the subscriber unit comprising:

a receiver for receiving the program guide information and the operating characteristics of the communication system;

a microphone employed by a subscriber for oral input of a selection code;

a camera operative to take a picture of the subscriber when located in a field of view of the camera;

a processor operative to associate speech characteristics of each of a multiplicity of speakers with images of each of the multiplicity of speakers;

an image processor operatively associated with the camera and the processor and operative to compare the picture of the subscriber to at least one of the images of each of the multiplicity of speakers and to determine whether the picture of the subscriber is substantially similar to an image of a speaker; and

a speech recognition unit operatively associated with the microphone and the processor and responding to the selection code when orally inputted by any of the multiplicity of speakers, the speech recognition unit being customized to respond only to the selection code inputted orally by the subscriber and to enable selection of a requested one of the operating characteristics of the communication system associated with the selection code upon a determination that the following coexist;

the picture of the subscriber orally inputting the selection code is substantially similar to the image of the speaker;

speech characteristics of the subscriber orally inputting the selection code substantially match speech characteristics associated with the speaker; and

the selection code orally inputted by the subscriber is a legitimate selection code associated with the requested one of the operating characteristics of the communication system.

29. A selection method for exclusively selecting a user whose oral input of a voice command for selecting a requested one of operating characteristics of a program guide selection communication system from among a plurality of operating characteristics of the system which are displayed on a display will be executed, the method comprising:

providing a speech recognition unit which is operative to recognize speech characteristics of a multiplicity of speakers from which the user is selected so that an oral expression of the voice command by any one of the multiplicity of speakers is recognizable by the speech recognition unit;

associating the speech characteristics of each of the multiplicity of speakers with images of each of the multiplicity of speakers; and

selecting the user as the exclusive speaker whose oral input of the voice command will be executed if the following are simultaneously satisfied;

a picture of the user taken by a camera when the user orally inputs the voice command is substantially similar to an image of one of the multiplicity of speakers;

speech characteristics of the user orally inputting the voice command substantially match speech characteristics associated with said one of the multiplicity of speakers; and

the voice command orally inputted by the user is a legitimate voice command associated with the requested one of the operating characteristics of the communication system.

30. A method for executing an orally inputted command for selecting a requested one of operating characteristics of a program guide selection communication system from among a plurality of operating characteristics of the system which are displayed on a display, the orally inputted command being recognizable by a speech recognition unit whenever any one of a plurality of speakers expresses orally the command, the method comprising:

detecting the orally inputted command;

verifying that the following are simultaneously satisfied;

speech characteristics determined from the orally inputted command substantially match speech characteristics associated with one of the plurality of speakers;

a picture of a user which is taken by a camera when the orally inputted command is detected substantially matches an image of said one of the plurality of speakers; and

the command is a legitimate command associated with the requested one of the operating characteristics of the communication system;

determining, in response to a positive result of said verifying step, that the command was expressed by the user and is to be executed; and

executing the command in response to said determining step.

31. A voice-activated subscriber unit of a communication system in which an orally inputted command for selecting a requested one of operating characteristics of the program guide selection communication system from among a plurality of operating characteristics of the system which are displayed on a display is executed, the subscriber unit comprising:

a speech recognition unit operative to detect the orally inputted command, the orally inputted command being recognizable by the speech recognition unit whenever any one of a plurality of speakers expresses orally the command;

a camera; and

a processor operatively associated with the speech recognition unit and the camera and operative to generate a verification that the following are simultaneously satisfied;

speech characteristics determined by the speech recognition unit from the orally inputted command substantially match speech characteristics associated with one of the plurality of speakers;

a picture of a user taken by the camera when the orally inputted command is detected substantially matches an image of said one of the plurality of speakers; and

the command is a legitimate command associated with the requested one of the operating characteristics of the communication system, wherein

the processor is further operative to generate a determination in response to said verification that the command was expressed by the user and is to be executed, and the voice recognition unit is further operative to execute the command in response to said determination.