Authentication for recognition systems

• US 9,619,645 B2
• Filed: 04/04/2013
• Issued: 04/11/2017
• Est. Priority Date: 04/04/2013
• Status: Active Grant

• Current Assignee: Cypress Semiconductor Corporation (Infineon Technologies AG)
• Original Assignee: Cypress Semiconductor Corporation (Infineon Technologies AG)
• Inventors: Bapat, Ojas
• Primary Examiner(s): He, Jialong
• Assistant Examiner(s): WANG, YI SHENG
• Application Number:
  US13/856,671
• Publication Number:
  US 20140303983A1
• Time in Patent Office: 1,468 Days
• Field of Search: None
• CPC Class Codes: B60R 16/0373 Voice control in general G10L
• CPC Class Codes: B60R 25/257 Voice recognition
• CPC Class Codes: G05B 19/00 Programme-control systems
• CPC Class Codes: G06F 21/44 Program or device authentication
• CPC Class Codes: G10L 15/20 Speech recognition techniques specially adapted for robustness in adverse environments, e.g. in noise, of stress induced speech G10L21/02 takes precedence
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 17/22 Interactive procedures; Man-machine interfaces
• CPC Class Codes: H04K 1/00 Secret communication

Abstract

Embodiments include a method, apparatus, and computer program product for authentication for speech recognition. The method can include sensing an authentication device with a target device. One or more decoded voice commands can be processed after verification of the authentication device by the target device. Further, one or more decoded voice commands can be executed by the target device.

Claims

1. A method for authentication for speech recognition, the method comprising:

sensing an authentication device with a target device;

processing one or more decoded voice commands with the authentication device and the target device after a verification of the authentication device by the target device;

executing the one or more decoded voice commands from the authentication device when a distance between the authentication device and the target device is greater than a predetermined distance from the target device; and

executing the one or more decoded voice commands from the target device when the distance between the authentication device and the target device is less than the predetermined distance from the target device.

2. The method of claim 1, wherein the sensing comprises activating one or more speech recognition engines after the verification of the authentication device by the target device.

3. The method of claim 1, wherein the processing comprises receiving the one or more decoded voice commands at the target device.

4. The method of claim 1, wherein the processing comprises removing one or more ambient conditions from the one or more decoded voice commands.

5. The method of claim 4, wherein the removing comprises canceling noise, canceling an echo, removing reverberation, or a combination thereof from the one or more decoded voice commands.

6. The method of claim 1, wherein the processing comprises processing the one or more decoded voice commands based on a learning algorithm that incorporates one or more past decoded utterances.

7. The method of claim 6, wherein the processing the one or more decoded voice commands based on the learning algorithm comprises requesting user clarification when a plurality results are associated with the one or more decoded voice commands.

8. An authentication apparatus for speech recognition, the apparatus comprising:

a speech recognition engine;

an authentication module configured to sense an authentication device; and

a command module configured to;

process one or more decoded voice commands from the authentication device and the speech recognition engine after a verification of the authentication device;

execute the one or more decoded voice commands from the authentication device when a distance between the authentication device and a target device associated with the speech recognition engine is greater than a predetermined distance from the target device; and

execute the one of more decoded voice commands from the target device when the distance between the authentication device is less than the predetermined distance from the target device.

9. The authentication apparatus of claim 8, wherein the authentication device comprises at least one of a smart card, a radio frequency identification device, a mobile device, or a smart key device.

10. The authentication apparatus of claim 8, wherein the authentication device comprises:

a transmitter configured to transmit one or more voice commands to the command module.

11. The authentication apparatus of claim 8, wherein the authentication module is configured to receive an authorization signal transmitted over a wireless communication link and the speech recognition engine is configured to receive one or more voice commands.

12. The authentication apparatus of claim 8, wherein the authentication module is configured to authenticate the authentication device based on an authorization signal transmitted over a wireless communication link and to output an activation signal to the speech recognition engine.

13. The authentication apparatus of claim 8, wherein the authentication device comprises a transmitter configured to transmit a first voice command to the speech recognition engine, and wherein the speech recognition engine is configured to receive a second voice command, the speech recognition engine configured to process either the first or the second voice command.

14. The authentication apparatus of claim 13, wherein the speech recognition engine is configured to process either the first or the second voice command based on a location of the authentication device.

15. The authentication apparatus of claim 8, wherein the command module is configured to process the one or more decoded voice commands based on a learning algorithm that incorporates past decoded utterances.

16. The authentication apparatus of claim 8, wherein the command module is configured to request user clarification when a plurality of results is associated with the one or more decoded voice commands.

17. A non-transitory computer readable medium having stored therein one or more sequences of one or more instructions for execution by one or more processors to perform a method for authentication for speech recognition, the method comprising:

sensing an authentication device with a target device;

processing one or more decoded voice commands by the authentication device and the target device after a verification of the authentication device by the target device; and

executing the one or more decoded voice commands from the authentication device when a distance between the authentication device and the target device is greater than a predetermined distance from the target device; and

executing the one or more decoded voice commands from the target device when the distance between the authentication device and the target device is less than the predetermined distance from the target device.

18. The non-transitory computer readable medium of claim 17, wherein the processing comprises selecting a first voice command from the authentication device or a second voice command from the target device based on a location of the authentication device relative to the target device.

19. The non-transitory computer readable medium of claim 17, wherein the processing comprises processing the one or more decoded voice commands based on a learning algorithm that incorporates one or more past decoded utterances.