Localized wakeword verification

A non-transitory computer-readable medium comprising program instructions stored thereon that are executable by at least one processor such that a first networked microphone device is configured to:

• receive, via at least one microphone of the first networked microphone device, sound data;
• determine, via a wake-word engine, that at least a first portion of the sound data is representative of a wake word, wherein the wake-word engine is configured to receive as input the sound data via the at least one microphone;
• determine that a second networked microphone device has been added to a media playback system, wherein the first networked microphone device is a member of the media playback system;
• based on determining that the first portion of the sound data is representative of the wake word and that the second networked microphone device has been added to the media playback system, transmit, via a network interface of the first networked microphone device, the first portion of the sound data to the second networked microphone device;
• begin determining a command, based on at least a second portion of the sound data, to be performed by the first networked microphone device;
• receive, from the second networked microphone device, an indication of whether the first portion of the sound data is representative of the wake word;
• and
• output a response indicative of whether the first portion of the sound data is representative of the wake word.

A method comprising:

• receiving, via at least one microphone of a first networked microphone device, sound data;
• determining, via a wake-word engine of the first networked microphone device, that at least a first portion of the sound data is representative of a wake word, wherein the wake-word engine is configured to receive as input the sound data via the at least one microphone;
• determining that a second networked microphone device has been added to a media playback system, wherein the first networked microphone device is a member of the media playback system;
• based on determining that the first portion of the sound data is representative of the wake word and that the second networked microphone device has been added to the media playback system, transmitting, by the first networked microphone device via a network interface of the first networked microphone device, the first portion of the sound data to the second networked microphone device;
• begin determining, by the first networked microphone device, a command, based on at least a second portion of the sound data, to be performed by the first networked microphone device;
• receiving, from the second networked microphone device, an indication of whether the first portion of the sound data is representative of the wake word;
• and
• outputting a response indicative of whether the first portion of the sound data is representative of the wake word.