APPLIANCES FOR PROVIDING USER-SPECIFIC RESPONSE TO VOICE COMMANDS

• US 20150120294A1
• Filed: 10/30/2013
• Published: 04/30/2015
• Est. Priority Date: 10/30/2013
• Status: Active Grant

• Current Assignee: Haier US Appliance Solutions, Inc. DBA GE Appliances (Haier Group Company)
• Original Assignee: General Electric Company
• Inventors: Gardner, William Everette, Hitzelberger, Joel Erik, Wait, Keith Wesley
• Granted Patent: US 9,406,297 B2
• Time in Patent Office: Days
• US Class Current: 704/235
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 17/00 Speaker identification or verification techniques
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command
• CPC Class Codes: G10L 2015/227 of the speaker; Human-factor methodology

Abstract

Generally the present disclosure is directed to appliances that provide a user-specific response to a received voice command. In particular, the appliance can store a plurality of voice samples respectively associated with a plurality of users. The appliance can also store one or more preferences for each of the plurality of users. For example, the preferences can be input by the user and/or learned or inferred over time. When the appliance receives a human speech signal or voice command, it can match the received speech signal against one or more of the plurality of voice samples to identify the user. The preferences stored and associated with the identified user can then be obtained and the appliance can perform any requested operations in accordance with the obtained preferences. In such fashion, the appliance can provide a user-specific response to a received voice command.

Claims

1. A method for operating an appliance, the method comprising:

receiving a human speech signal;

identifying one of a plurality of enrolled users as a source of the human speech signal;

obtaining one or more preset preferences associated with the identified enrolled user and stored in a memory;

converting the human speech signal to textual information;

determining one or more appliance operations requested by the human speech signal based on the textual information; and

performing the one or more appliance operations in accordance with the one or more preset preferences.

2. The method of claim 1, wherein identifying one of the plurality of enrolled user comprises matching one or more biometrics of the human speech signal to one of a plurality of voice samples respectively associated with the plurality of enrolled users.

3. The method of claim 1, further comprising obtaining one or more default preferences when one of the plurality of enrolled users cannot be identified as the source of the human speech signal, wherein the appliance operations are performed in accordance with the one or more default preferences.

4. The method of claim 3, wherein obtaining one or more default preferences comprises:

selecting one of a plurality of default profiles based on the human speech signal; and

obtaining one or more default preferences associated with the selected default profile;

wherein the plurality of default profiles include a default juvenile profile and a default adult profile.

5. The method of claim 1, further comprising enrolling a new user when one of the plurality of enrolled users cannot be identified as the source of the human speech signal, wherein enrolling the new user comprises:

obtaining a voice sample from the new user; and

associating the voice sample with a user identifier associated with the new user.

6. The method of claim 5, wherein enrolling the new user further comprises obtaining a plurality of preferences to be stored and associated with the user identifier associated with the new user.

7. The method of claim 1, further comprising, prior to performing the one or more appliance operations:

identifying one or more variable parameters associated with the one or more appliance operations that are not addressed by the one or more preset preferences; and

obtaining from the identified enrolled user one or more supplemental preferences with respect to the one or more variable parameters;

wherein performing the one or more appliance operations comprises performing the one or more appliance operations in accordance with the one or more supplemental preferences.

8. The method of claim 7, further comprising associating the one or more supplemental preferences with the identified enrolled user.

9. The method of claim 1, wherein the appliance comprises a refrigerator having a water dispensing system, and wherein the one or more preset preferences respectively describe one or more aspects of operation of the water dispensing system.

10. The method of claim 9, wherein the one or more preferences comprises a preferred water temperature, a preferred water flavoring, a preferred ice style, or a preferred water carbonation level.

11. An appliance comprising:

a speech-to-text module configured to convert a human speech signal into textual information;

a user identification module configured to identify one of a plurality of enrolled users based on an analysis of the human speech signal; and

a feature processing module configured to determine one or more requested appliance actions based on the textual information;

wherein the appliance is configured to perform operations, the operations comprising;

accessing from a memory one or more preferences associated with the identified enrolled user; and

performing the requested appliance actions in accordance with the one or more preferences.

12. The appliance of claim 11, wherein the user identification module is configured to identify the one of the plurality of enrolled users by performing a matching routine with respect to the human speech signal and a plurality of voice samples respectively stored in the memory.

13. The appliance of claim 11, further comprising a user enrollment module configured to enroll a new user when the user identification module is unable to identify one of the plurality of enrolled users based on the analysis of the human speech signal.

14. The appliance of claim 13, wherein the user enrollment module is configured to enroll the new user by performing operations, the operations comprising:

receiving a voice sample from the new user;

receiving one or more preferences from the new user; and

associating the voice sample and the one or more preferences with the new user in the memory.

15. The appliance of claim 11, wherein the appliance is further configured to perform further operations comprising accessing from the memory one or more default preferences when the user identification module is unable to identify one of the plurality of enrolled users based on the analysis of the human speech signal.

16. The appliance of claim 11, further comprising a user interface, wherein the user interface comprises a display and a microphone.

17. An appliance comprising:

at least one processor; and

a non-transitory computer readable medium storing instructions that, when executed by the at least one processor, cause the appliance to perform operations, the operations comprising;

receiving a human speech signal from a user;

determining whether the user can be identified based on the human speech signal;

when the user cannot be identified based on the human speech signal, performing an enrollment process to enroll the user; and

when the user can be identified based on the human speech signal, accessing one or more previously obtained preferences associated with the user and performing one or more requested appliance operations in accordance with the one or more previously obtained preferences.

18. The appliance of claim 17, wherein determining whether the user can be identified based on the human speech signal comprises respectively matching one or more biometrics of the human speech signal against a plurality voice samples respectively associated with a plurality of enrolled users.

19. The appliance of claim 17, wherein performing the enrollment process to enroll the user comprises obtaining a voice sample from the user.

20. The appliance of claim 17, wherein the non-transitory computer readable medium stores further instructions that, when executed by the at least one process, cause the appliance to perform further operations comprising:

converting the human speech signal to textual information; and

identifying the one or more requested appliance operations based on the textual information.