Voice control of remote device by disabling wakeword detection

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.

A system comprising:

• at least one processor;
• and
• memory including instructions operable to be executed by the at least one processor to to cause the system to:
• receive, by a first device in a first environment, from a remote server, an instruction to begin a remote control session between the first device and a second device in a second environment physically remote from the first environment;
• disable wakeword detection in response to receiving the instruction to begin the remote control session;
• generate, by the first device, first audio data;
• send at least a portion of the first audio data to the second device, the first audio data corresponding to a communication from the first device to the second device;
• generate, while the wakeword detection is disabled, second audio data corresponding to the communication from the first device to the second device and including a command to perform an action;
• and
• send at least a portion of the second audio data to the second device.

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;
• receiving, from a remote server, an instruction to disable wakeword detection;
• disabling the wakeword detection;
• generating, while the wakeword detection is disabled, second audio data corresponding to the communication from the first device to the second device and including a command to perform an action;
• sending at least a portion of the second audio data to the second device;
• receiving, from the remote server, a second instruction to enable the wakeword detection;
• and
• enabling the wakeword detection.