Networked devices, systems, and methods for intelligently deactivating wake-word engines
In one aspect, a playback deice is configured to identify in an audio stream, via a second wake-word engine, a false wake word for a first wake-word engine that is configured to receive as input sound data based on sound detected by a microphone. The first and second wake-word engines are configured according to different sensitivity levels for false positives of a particular wake word. Based on identifying the false wake word, the playback device is configured to (i) deactivate the first wake-word engine and (ii) cause at least one network microphone device to deactivate a wake-word engine for a particular amount of time. While the first wake-word engine is deactivated, the playback device is configured to cause at least one speaker to output audio based on the audio stream. After a predetermined amount of time has elapsed, the playback device is configured to reactivate the first wake-word engine.
1 . A first playback device comprising:
at least one microphone;
one or more processors;
at least one non-transitory computer-readable medium; and
program instructions stored on the at least one non-transitory computer-readable medium that are executable by the one or more processors such that the first playback device is configured to:
operate in a group including at least a second playback device;
before identifying a given wake-word received via the at least one microphone, receive, from the second playback device, an indication that the first playback device is not to respond to the given wake-word for a given amount of time;
based on receiving the indication, deactivate wake-word response output for the given wake-word for the given amount of time while wake-word response output for at least one other wake-word remains activated for the given amount of time;
while wake-word response output for the given wake-word is deactivated for the first playback device for the given amount of time, (i) identify, by the first playback device, the given wake-word and (ii) forgo, by the first playback device, responding to the given wake-word; and
after foregoing responding to the given wake-word, reactivate wake-word response output for the given wake-word based on the given amount of time elapsing.
2 . The first playback device of claim 1 , wherein the indication that the first playback device is not to respond to the given wake-word comprises an indication that an identification of the given wake-word by the first playback device is likely to be a false positive.
3 . The first playback device of claim 1 , wherein the given wake-word identified while wake-word response output for the given wake-word is deactivated for the given amount of time comprises audio that is phonetically similar to the given wake-word.
4 . The first playback device of claim 3 , wherein the given wake-word identified while wake-word response output for the given wake-word is deactivated for the given amount of time comprises spectral characteristics that match spectral characteristics of the given wake-word.
5 . The first playback device of claim 1 , wherein the program instructions that are executable by the one or more processors such that the first playback device is configured to deactivate wake-word response output for the given wake-word for the given amount of time comprise program instructions that are executable by the one or more processors such that the first playback device is configured to:
after identifying the given wake-word, suppress output of a response to the given wake-word.
6 . The first playback device of claim 1 , wherein the program instructions that are executable by the one or more processors such that the first playback device is configured to deactivate wake-word response output for the given wake-word for the given amount of time comprise program instructions that are executable by the one or more processors such that the first playback device is configured to:
deactivate wake-word response output for the given wake-word while the first playback device is part of the group.
7 . The first playback device of claim 1 , further comprising program instructions stored on the at least one non-transitory computer-readable medium that are executable by the one or more processors such that the first playback device is configured to:
after the given amount of time has elapsed, leave the group.
8 . The first playback device of claim 1 , further comprising program instructions stored on the at least one non-transitory computer-readable medium that are executable by the one or more processors such that the first playback device is configured to:
while wake-word response output for the given wake-word is deactivated for the first playback device for the given amount of time, (iii) identify, by the first playback device, at least one other wake-word and (iv) respond to the at least one other wake-word.
9 . A non-transitory computer-readable medium, wherein the non-transitory computer-readable medium is provisioned with program instructions that, when executed by one or more processors, cause a first playback device to:
operate in a group including at least a second playback device;
before identifying a given wake-word received via at least one microphone, receive, from the second playback device, an indication that the first playback device is not to respond to the given wake-word for a given amount of time;
based on receiving the indication, deactivate wake-word response output for the given wake-word for the given amount of time while wake-word response output for at least one other wake-word remains activated for the given amount of time;
while wake-word response output for the given wake-word is deactivated for the first playback device for the given amount of time, (i) identify, by the first playback device, the given wake-word and (ii) forgo, by the first playback device, responding to the given wake-word; and
after foregoing responding to the given wake-word, reactivate wake-word response output for the given wake-word based on the given amount of time elapsing.
10 . The non-transitory computer-readable medium of claim 9 , wherein the indication that the first playback device is not to respond to the given wake-word comprises an indication that an identification of the given wake-word by the first playback device is likely to be a false positive.
11 . The non-transitory computer-readable medium of claim 9 , wherein the given wake-word identified while wake-word response output for the given wake-word is deactivated for the given amount of time comprises audio that is phonetically similar to the given wake-word.
12 . The non-transitory computer-readable medium of claim 11 , wherein the given wake-word identified while wake-word response output for the given wake-word is deactivated for the given amount of time comprises spectral characteristics that match spectral characteristics of the given wake-word.
13 . The non-transitory computer-readable medium of claim 9 , wherein the program instructions that, when executed by one or more processors, cause the first playback device to deactivate wake-word response output for the given wake-word for the given amount of time comprise program instructions that, when executed by one or more processors, cause the first playback device to:
after identifying the given wake-word, suppress output of a response to the given wake-word.
14 . The non-transitory computer-readable medium of claim 9 , wherein the program instructions that, when executed by one or more processors, cause the first playback device to deactivate wake-word response output for the given wake-word for the given amount of time comprise program instructions that, when executed by one or more processors, cause the first playback device to:
deactivate wake-word response output for the given wake-word while the first playback device is part of the group.
15 . The non-transitory computer-readable medium of claim 9 , wherein the non-transitory computer-readable medium is also provisioned with program instructions that, when executed by one or more processors, cause the first playback device to:
after the given amount of time has elapsed, leave the group.
16 . The non-transitory computer-readable medium of claim 9 , wherein the non-transitory computer-readable medium is also provisioned with program instructions that, when executed by one or more processors, cause the first playback device to:
while wake-word response output for the given wake-word is deactivated for the first playback device for the given amount of time, (iii) identify, by the first playback device, at least one other wake-word and (iv) respond to the at least one other wake-word.
17 . A method carried out by a first playback device, the method comprising:
operating in a group including at least a second playback device;
before identifying a given wake-word received via at least one microphone, receiving, from the second playback device, an indication that the first playback device is not to respond to the given wake-word for a given amount of time;
based on receiving the indication, deactivating wake-word response output for the given wake-word for the given amount of time while wake-word response output for at least one other wake-word remains activated for the given amount of time;
while wake-word response output for the given wake-word is deactivated for the first playback device for the given amount of time, (i) identifying, by the first playback device, the given wake-word and (ii) forgoing, by the first playback device, responding to the given wake-word; and
after foregoing responding to the given wake-word, reactivating wake-word response output for the given wake-word based on the given amount of time elapsing.
18 . The method of claim 17 , wherein deactivating wake-word response output for the given wake-word for the given amount of time comprises:
after identifying the given wake-word, suppressing output of a response to the given wake-word.
19 . The method of claim 17 , further comprising:
while wake-word response output for the given wake-word is deactivated for the first playback device for the given amount of time, (iii) identifying, by the first playback device, at least one other wake-word and (iv) responding to the at least one other wake-word.
20 . The method of claim 17 , wherein the indication that the first playback device is not to respond to the given wake-word comprises an indication that an identification of the given wake-word by the first playback device is likely to be a false positive.