Wakeword detection using a secondary microphone

Patent metadata

Field	Value
Publication number	US-11024290-B2
Application number	US-201916272938-A
Country	US
Kind code	B2
Filing date	Feb 11, 2019
Priority date	Feb 11, 2019
Publication date	Jun 1, 2021
Grant date	Jun 1, 2021

Abstract

Techniques for capturing spoken user inputs while a device is prevented from capturing such spoken user inputs are described. When a first device becomes incapable of capturing spoken user inputs intended for a system, a second device, for capturing such spoken user inputs, may be identified. The second device may be identified based on the second device being connected to a same vehicle computing system as the first device. The second device may be enabled to capture spoken user inputs, intended for the system, until the first device is again able to capture such spoken user inputs.

First claim

What is claimed is:

1. A system, comprising:
at least one processor; and
at least one memory comprising instructions that, when executed by the at least one processor, cause the system to:
receive a first indicator representing a device status of a first device corresponding to a first device identifier;
after receiving the first indicator, determine a second device identifier, corresponding to a second device, is represented in a group of device identifiers including the first device identifier, the first device identifier and the second device identifier being represented in the group of device identifiers based at least in part on the first device and the second device each receiving same previously spoken audio including a wakeword;
associate the second device identifier with a second indicator representing the second device is processing on behalf of the first device;
send, to the first device, an instruction to ceasing processing of audio to detect the wakeword;
receive, from the second device, audio data representing a spoken user input;
determine the second device identifier is associated with the second indicator; and
perform speech processing on the audio data as if the audio data was received from the first device.

2. The system of claim 1 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
receive a third indicator representing a second device status of the first device;
after receiving the first indicator, receive, from the first device, a third device identifier corresponding to a third device connected to the first device using Bluetooth protocols;
determine a profile associated with a plurality of device identifiers including the first device identifier;
determine the profile is associated with the third device identifier; and
send, to the first device, a second instruction to ceasing processing of second audio to detect the wakeword.

3. The system of claim 1 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
receive a third indicator representing a second device status of the first device;
after receiving the third indicator, determine the first device is to be invoked to process second audio to detect the wakeword;
disassociate the third indicator from the second device identifier;
after disassociating the third indicator, receive, from the second device, second audio data representing a second spoken user input; and
perform speech processing on the second audio data as if the second audio data was received from the second device.

4. The system of claim 1 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
receive a third indicator representing a second device status of the first device;
receive a vehicle identifier corresponding to a vehicle to which the first device is connected using Bluetooth protocols;
send, to the vehicle, a request for at least one device identifier representing at least one other device connected to the vehicle via Bluetooth protocols;
receive, from the vehicle, a fourth indicator representing a third device is connected to the vehicle using Bluetooth protocols, the third device corresponding to a third device identifier;
determine a profile associated with a plurality of device identifiers including the first device identifier;
determine the profile is associated with the third device identifier; and
send, to the vehicle, a second instruction to cause the first device to cease processing second audio to detect the wakeword.

5. A system, comprising:
at least one processor; and
at least one memory comprising instructions that, when executed by the at least one processor, cause the system to:
receive an indicator representing a device status of a first device corresponding to a first device identifier;
based at least in part on the device status, determine a second device identifier, corresponding to a second device, is represented in a group of device identifiers including the first device identifier; and
based at least in part on determining the second device identifier is represented in the group of device identifiers, send, to the first device, an instruction to cease performing wakeword detection.

6. The system of claim 5 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
receive a second indicator representing a second device status of the first device;
receive a vehicle identifier corresponding to a vehicle to which the first device is connected;
send, to the vehicle, a request for at least one device identifier representing at least one other device connected;
receive, from the vehicle, a third indicator representing a third device connected to the vehicle, the third device corresponding to a third device identifier;
determine a profile associated with a plurality of device identifiers including the first device identifier;
determine the profile is associated with the third device identifier; and
cause the first device to cease performing wakeword detection.

7. The system of claim 6 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
cause the first device to cease performing wakeword detection by sending, to the vehicle, a second instruction to cause the first device to cease performing wakeword detection.

8. The system of claim 5 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
receive a second indicator representing a second device status of the first device;
based at least in part on the second device status, receive, from the first device, a third device identifier corresponding to a third device connected to the first device via a wireless connection; and
cause the first device to cease performing wakeword detection.

9. The system of claim 5 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
receive a second indicator representing a second device status of the first device;
based at least in part on the second device status, determine a profile associated with a plurality of device identifiers including the first device identifier and a third device identifier corresponding to a third device;
determine, in the profile, that the first device identifier is associated with first position data;
determine, in the profile, that the third device identifier is associated with second position data substantially corresponding to the first position data; and
cause the first device to cease performing wakeword detection.

10. The system of claim 5 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
receive a second indicator representing a second device status of the first device;
based at least in part on the second device status, determine a profile associated with a plurality of device identifiers including the first device identifier and a third device identifier corresponding to a third device;
determine, in the profile, that the first device identifier is associated with network identifying information;
determine, in the profile, that the third device identifier is associated with the network identifying information; and
cause the first device to cease per

Assignees

• Amazon Tech Inc

Inventors

• Mitchell Andrew
• Nagy Gabor

Classifications

• G10L15/22

  Procedures used during a speech recognition process, e.g. man-machine dialogue · CPC title

• G10L2015/088

  Word spotting · CPC title

• G10L2015/223

  Execution procedure of a spoken command · CPC title

• G10L15/30

  Distributed recognition, e.g. in client-server systems, for mobile phones or network applications · CPC title

• G10L15/32 Primary

  Multiple recognisers used in sequence or in parallel; Score combination systems therefor, e.g. voting systems · CPC title