Device designation for audio input monitoring

• US 10,210,868 B2
• Filed: 04/17/2017
• Issued: 02/19/2019
• Est. Priority Date: 06/24/2014
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google LLC (Alphabet Inc.)
• Inventors: Faaborg, Alexander James
• Primary Examiner(s): Riley, Marcus T
• Application Number:
  US15/489,288
• Publication Number:
  US 20170221487A1
• Time in Patent Office: 673 Days
• Field of Search: None
• CPC Class Codes: G06F 3/162 Interface to dedicated audio devices, e.g. audio drivers, interface to CODECs
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G10L 15/08 Speech classification or search
• 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 15/28 Constructional details of speech recognition systems
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• CPC Class Codes: G10L 2015/088 Word spotting
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command
• CPC Class Codes: G10L 25/78 Detection of presence or absence of voice signals switching of direction of transmission by voice frequency in two-way loud-speaking telephone systems H04M9/10

Abstract

A computing device comprises at least one processor, and at least one module operable by the at least one processor to designate a particular computing device from a plurality of computing devices to process audio input, wherein the computing device comprises a first computing device from the plurality of computing devices. The at least one module may be further operable by the at least one processor to, if the particular computing device is not the first computing device, cease processing of audio input, and if the particular computing device is the first computing device, receive first audio input and process the first audio input to determine whether the first audio input includes a predetermined audio command.

Claims

1. A method comprising:

receiving, by a first computing device of a plurality of computing devices each of which are associated with a user account and are located in physical proximity to one another, a spoken audio input that includes a spoken audio trigger, wherein the spoken audio trigger is also received by at least a second computing device from the plurality of computing devices, wherein a user account associated with the first computing device and a user account associated with the second computing device are the same user account;

sending, by the first computing device and to a different computing device, an indication of the received spoken audio trigger;

receiving, by the first computing device and from the different computing device, an indication of a device designated to process the spoken audio input for a spoken audio command, wherein the device designated to process the spoken audio input is based at least in part on a quality of the spoken audio trigger received by the first computing device;

determining, by the first computing device, based on the indication of the device designated to process the spoken audio input, whether the first computing device or the second computing device is the device designated to process the spoken audio input for the spoken audio command; and

responsive to determining that the first computing device is the device designated to process the spoken audio input for the spoken audio command, processing, by the first computing device, the spoken audio input for the spoken audio command.

2. The method of claim 1, further comprising:

sending, by the first computing device and to the second computing device, a command to temporarily refrain from processing spoken audio input.

3. The method of claim 1, wherein the indication of the device designated to process the spoken audio input includes a device identifier for the device designated to process the spoken audio input, and wherein determining whether the first computing device or the second computing device is the device designated to process the spoken audio input comprises:

determining, by the first computing device, whether the device identifier for the device designated to process the spoken audio input corresponds to a device identifier for the first computing device; and

responsive to determining that the device identifier for the device designated to process the spoken audio input corresponds to the device identifier for the first computing device, determining, by the first computing device, that the first computing device is the device designated to process the spoken audio input.

4. The method of claim 1, wherein the second computing device and the different computing device are the same computing device.

5. The method of claim 1, further comprising:

sending, by the first computing device and to the different computing device, an indication of a type of the first computing device,

wherein the device designated to process the spoken audio input for the spoken audio command is based at least in part on the type of the first computing device.

6. The method of claim 1, further comprising:

responsive to determining that the first computing device is not the device designated to process the spoken audio input, refraining, by the first computing device, from processing the spoken audio input.

7. The method of claim 6, wherein refraining from processing the spoken audio input comprises temporarily deactivating, by the first computing device, an audio monitoring module.

8. The method of claim 1,

wherein the spoken audio trigger includes a hotword, and

wherein processing the spoken audio input for the spoken audio command comprises processing, by the first computing device, a portion of the spoken audio command that is received after receiving the hotword.

9. The method of claim 8, wherein processing the portion of the spoken audio input that is received after receiving the hotword further comprises performing, by the first computing device, speech recognition on the portion of the spoken audio input that is received after receiving the hotword.

10. The method of claim 1, further comprising:

determining, by the first computing device, whether the first computing device is a device designated to execute the spoken audio command included in the spoken audio input;

responsive to determining that the first computing device is the device designated to execute the spoken audio command included in the spoken audio input, executing, by the first computing device, the spoken audio command included in the spoken audio input.

21. The method of claim 1, wherein the quality of the spoken audio trigger includes at least one of:

a volume of the spoken audio trigger,

a signal-to-noise ratio of the spoken audio trigger, or

a ratio between speech included in the spoken audio trigger and other sound included in the spoken audio trigger.

11. A first computing device comprising:

at least one processor; and

a memory comprising instructions that, when executed by the at least one processor, cause the at least one processor to;

receive a spoken audio input that includes a spoken audio trigger, wherein the spoken audio trigger is also received by at least one other computing device from a plurality of computing devices, wherein the plurality of computing devices includes the first computing device and a second computing device, wherein a user account associated with the first computing device and a user account associated with the second computing device are the same user account, and wherein each computing device of the plurality of computing devices are located in physical proximity to one another;

send, to a different computing device, an indication of the received spoken audio trigger;

receive, from the different computing device, an indication of a device designated to process the spoken audio input for a spoken audio command, wherein the device designated to process the spoken audio input is based at least in part on a quality of the spoken audio trigger received by the first computing device;

determine, based on the indication of the device designated to process the spoken audio input, whether the first computing device or the second computing device is the device designated to process the spoken audio input for the spoken audio command; and

responsive to determining that the first computing device is the device designated to process the spoken audio input for the spoken audio command, process the spoken audio input for the spoken audio command.

12. The first computing device of claim 11, wherein the indication of the device designated to process the spoken audio input includes a device identifier for the device designated to process the spoken audio input, and wherein execution of the instructions causes the at least one processor to determine whether the first computing device or the second computing device is the device designated to process the spoken audio input by causing the at least one processor to:

determine whether the device identifier for the device designated to process the spoken audio input corresponds to a device identifier for the first computing device; and

responsive to determining that the device identifier for the device designated to process the spoken audio input corresponds to the device identifier for the first computing device, determine that the first computing device is the device designated to process the spoken audio input.

18. The first computing device of claim 11, wherein execution of the instructions further causes the at least one processor to send, to the second computing device, a command to temporarily refrain from processing spoken audio input.

19. The first computing device of claim 11, wherein execution of the instructions further causes the at least one processor to refrain from processing the spoken audio input in response to determining that the first computing device is not the device designated to process the spoken audio input.

20. The first computing device of claim 11, wherein execution of the instructions further causes the at least one processor to process the spoken audio input for the spoken audio command by processing a portion of the spoken audio input that is received after receiving the spoken audio trigger.

13. A non-transitory computer-readable storage medium encoded with instructions that, when executed, cause at least one processor of a first computing device to:

receive a spoken audio input that includes a spoken audio trigger, wherein the spoken audio trigger is also received by at least one other computing device from a plurality of computing devices, wherein the plurality of computing devices includes the first computing device and a second computing device, wherein each computing device of the plurality of computing devices are associated with a user account, wherein a user account associated with the first computing device and a user account associated with the second computing device are the same user account, and wherein each computing device of the plurality of computing devices are located in physical proximity to one another;

receive, from the second computing device, an indication of a type of the second computing device;

determine, based at least in part on a type of the first computing device and the type of the second computing device, whether the first computing device or the second computing device is a device designated to process the spoken audio input for a spoken audio command; and

responsive to determining that the first computing device is the device designated to process the spoken audio input for the spoken audio command, process a portion of the spoken audio input that is received after the spoken audio trigger for the spoken audio command.

14. The non-transitory computer-readable storage medium of claim 13,

wherein execution of the instructions further cause the at least one processor to receive, from the second computing device, an indication of a context of the second computing device, and

wherein execution of the instructions cause the at least one processor to determine whether the first computing device or the second computing device is the device designated to process the spoken audio input for the spoken audio command based at least in part on a context of the first computing device and the context of the second computing device.

15. The non-transitory computer-readable storage medium of claim 13,

wherein execution of the instructions further cause the at least one processor to receive, from the second computing device, an indication of an audio quality of the spoken audio input received by the second computing device,

wherein execution of the instructions cause the at least one processor to determine whether the first computing device or the second computing device is the device designated to process the spoken audio input for the spoken audio command based at least in part on an audio quality of the spoken audio input received by the first computing device and the audio quality of the spoken audio input received by the second computing device.

16. The non-transitory computer-readable storage medium of claim 13, wherein execution of the instructions further causes the at least one processor to send, to the second computing device, a command to temporarily refrain from processing spoken audio input.

17. The non-transitory computer-readable storage medium of claim 13, wherein execution of the instructions further causes the at least one processor to refrain from processing the spoken audio input in response to determining that the first computing device is not the device designated to process the spoken audio input.