Voice control of remote device by disabling wakeword detection

Patent metadata

Field	Value
Publication number	US-10074371-B1
Application number	US-201715458628-A
Country	US
Kind code	B1
Filing date	Mar 14, 2017
Priority date	Mar 14, 2017
Publication date	Sep 11, 2018
Grant date	Sep 11, 2018

Abstract

A system configured to enable remote control to allow a first user to provide assistance to a second user. The system may receive a command from the second user granting remote control to the first user, enabling the first user to initiate a voice command on behalf of the second user. In some examples, the system may enable the remote control by treating a voice command originating from the first user as though it originated from the second user instead. For example, the system may receive the voice command from a first device associated with the first user but may route the voice command as though it was received by a second device associated with the second user. To enable this functionality, during a remote control session the first device may disable wakeword detection so that the voice command is correctly routed to the second device.

First claim

What is claimed is:

1. A computer-implemented method, comprising:
generating, by a first speech-controlled device in a first environment, first audio data using one or more microphones;
sending at least a portion of the first audio data to a second speech-controlled device in a second environment physically remote from the first environment, the first audio data corresponding to a communication from the first speech-controlled device to the second speech-controlled device;
detecting that a wakeword is represented in the first audio data;
generating second audio data including at least a portion of the first audio data following the wakeword, the second audio data corresponding to a first command to disable wakeword detection;
sending the second audio data to a remote server;
receiving, from the remote server in response to the first command, an instruction to disable wakeword detection;
disabling the wakeword detection;
generating, while the wakeword detection is disabled, third audio data corresponding to the communication from the first speech-controlled device to the second speech-controlled device and including a second command to perform a second action; and
sending at least a portion of the third audio data to the second speech-controlled device.

2. The computer-implemented method of claim 1 , further comprising:
detecting, using a wakeword detection component, that the wakeword is represented in the third audio data;
determining that the wakeword detection is disabled;
determining to ignore the wakeword;
detecting, using the wakeword detection component, that a second wakeword is represented in the third audio data, the second wakeword corresponding to a command to enable the wakeword detection; and
enabling the wakeword detection.

3. The computer-implemented method of claim 1 , further comprising, by the first speech-controlled device prior to receiving the instruction to disable the wakeword detection:
detecting, using the wakeword detection, that a second wakeword is represented in the first audio data;
generating fourth audio data including at least a portion of the first audio data following the second wakeword; and
sending the fourth audio data to the remote server, the fourth audio data corresponding to a third command to perform a third action.

4. The computer-implemented method of claim 1 , further comprising:
receiving fourth audio data originating from the second speech-controlled device;
outputting first audio corresponding to a first portion of the fourth audio data, the first audio having a first volume level;
generating fifth audio data using the one or more microphones;
detecting that the wakeword is represented in the fifth audio data;
outputting second audio corresponding to a second portion of the fourth audio data, the second audio having a second volume level that is less than the first volume level;
receiving a notification that the second speech-controlled device is granted remote control of the first speech-controlled device;
receiving sixth audio data originating from the second speech-controlled device;
outputting third audio corresponding to a first portion of the sixth audio data, the third audio having the first volume level;
generating, using the one or more microphones, seventh audio data corresponding to at least a portion of the third audio;
detecting that the wakeword is represented in the seventh audio data; and
outputting fourth audio corresponding to a second portion of the sixth audio data, the fourth audio having the first volume level.

5. A computer-implemented method, comprising:
generating, by a first device in a first environment, first audio data;
sending at least a portion of the first audio data to a second device in a second environment physically remote from the first environment, the first audio data corresponding to a communication from the first device to the second device;
detecting that a wakeword is represented in the first audio data;
generating second audio data including at least a portion of the first audio data following the wakeword, the second audio data corresponding to a first command to disable wakeword detection;
sending at least the second audio data to a remote server;
receiving, from the remote server in response to the first command, an instruction to disable wakeword detection;
disabling the wakeword detection;
generating, while the wakeword detection is disabled, third audio data corresponding to the communication from the first device to the second device and including a second command to perform an action; and
sending at least a portion of the third audio data to the second device.

6. The computer-implemented method of claim 5 , further comprising, by the first device prior to receiving the instruction to disable the wakeword detection:
detecting that the wakeword is represented in the first audio data;
generating fourth audio data including at least a portion of the first audio data following the wakeword; and
sending the fourth audio data to the remote server, the fourth audio data corresponding to a third command to perform a second action associated with a first user profile corresponding to the first device.

7. The computer-implemented method of claim 6 , further comprising, by the first device prior to receiving the instruction to disable the wakeword detection:
detecting that a second wakeword is represented in the first audio data, the second wakeword being different from the first wakeword;
generating fifth audio data including at least a portion of the first audio data following the second wakeword; and
sending the fifth audio data to the remote server, the fifth audio data corresponding to a fourth command to perform a third action associated with a second user profile corresponding to the second device.

8. The computer-implemented method of claim 5 , further comprising:
receiving, from the remote server, a second instruction to enable the wakeword detection; and
enabling the wakeword detection.

9. The computer-implemented method of claim 5 , further comprising:
detecting, using a wakeword detection component, that the wakeword is represented in the third audio data;
determining that the wakeword detection is disabled; and
determining to ignore the wakeword.

10. The computer-implemented method of claim 5 , further comprising:
detecting, using a wakeword detection component, that a second wakeword is represented in the third audio data, the second wakeword different than the first wakeword and corresponding to a third command to enable the wakeword detection; and
enabling the wakeword detection.

11. The computer-implemented method of claim 5 , further comprising, by the first device prior to receiving the instruction to disable the wakeword detection:
detecting that wakeword is represented in the first audio data;
generating fourth audio data including at least a portion of the first audio data following the wakeword; and
sending the fourth audio data to the remote server, the fourth audio data corresponding to a third command to perform a second action associated with a user profile corresponding to the second device.

12. The computer-implemented method of claim 5 , further comprising:
receiving fourth audio data originating from the second device;
outputting first audio corresponding to a first portion of the fourth audio data, the first audio having a first volume level;
generating fifth audio data;
detecting that the wakeword is represented in the fifth audio data;
outputting second audio corresponding to a second portion of the fourth audio data, the second audio having a second volume level

Assignees

• Amazon Tech Inc

Inventors

• Wang Peng
• Naidu Pathivada Rajsekhar

Classifications

• H04M2203/1016

  Telecontrol · CPC title

• G06F3/167

  Audio in a user interface, e.g. using voice commands for navigating, audio feedback · CPC title

• G10L15/08

  Speech classification or search · CPC title

• G10L15/22 Primary

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

• G10L2015/223

  Execution procedure of a spoken command · CPC title