Input detection windowing

1. A playback device comprising:

at least one microphone configured to detect sound; at least one processor; and

data storage having instructions stored thereon that are executed by the at least one processor to cause the playback device to perform functions comprising:

detecting a first input sound data stream comprising a wake word and a voice input; performing an action based on the voice input, wherein the action comprises initiating

playback of a playback queue;

while playing back the playback queue, detecting an event, the event being associated with the playback device or a system comprising the playback device, wherein the event comprises an indication of a track change associated with the playback queue, wherein the indication corresponds to a user input to change a trackvia a controller; and

responsive to the event comprising the indication of the track change, opening an input detection window for a given time period;

wherein during the given time period the at least one processor is arranged to perform functions comprising:

receiving, by the at least one processor, a second input sound data stream from the at least one microphone, wherein the second input sound data stream represents sound detected by the at least one microphone;

analyzing the second input sound data stream by the at least one processor for a plurality of keywords supported by the playback device;

determining, based on the analysis, that the second input sound data stream includes voice input data comprising a keyword;

wherein the keyword is one of the plurality of keywords supported by the playback device; and

responsive to the determining that the second input sound data stream includes voice input data comprising a keyword, causing a command corresponding to the keyword to be performed.

2. The playback device according to claim 1 , further comprising:

storing historical data in the data storage, the historical data including determined events and any associated commands; and

analyzing the historical data to adjust the given time period associated with the input detection window.

3. The playback device according to claim 2 , wherein analyzing the historical data comprises:

determining a frequency of the associated commands and a time period, relative to a time of the event, during which the associated commands were received by the playback device or a system comprising the playback device; and

setting the given time period based on the frequency and the time period.

4. The playback device according to claim 2 , wherein the given time period is associated with a user account of the playback device or a system comprising the playback device.

5. The playback device according to claim 1 , wherein outside of the input detection window, the second input sound data stream is not analyzed.

6. The playback device according to claim 1 , further comprising:

a network interface, and

the instructions stored on the data storage that are executed by the at least one processor further cause the playback device to perform functions comprising:

transmitting, via the network interface and during the input detection window, at least part of the second input sound data stream to a remote server for analysis;

receiving data including a remote command from the remote server, the remote command being supported by the playback device; and causing the media playback system to perform the remote command.

7. The playback device according to claim 1 , wherein the analyzing the second input data stream comprises determining a keyword by at least one of:

natural language processing to determine an intent, based on an analysis of the keyword in the second input sound data stream; and pattern-matching based on a predefined library of keywords and associated keywords.

8. A method to be performed by a playback device comprising at least one microphone configured to detect sound, the method comprising:

detecting a first input sound data stream comprising a wake word and a voice input; performing an action based on the voice input wherein the action comprises initiating

playback of a playback queue;

while playing back the playback queue, detecting an event associated with the playback device or a system comprising the playback device, wherein the event comprises an indication of a track change associated with the playback queue wherein the indication corresponds to a user input to change a track via a controller device;

opening, upon the detection of the event comprising the indication of the track change, an input detection window for a given time period; and

during the given time period:

receiving a second input sound data stream representing the sound detected by the at least one microphone;

analyzing the second input sound data stream for a plurality of keywords supported by the playback device;

determining based on the analysis, that the second input sound data stream includes voice input data comprising a keyword; wherein the keyword is one of the plurality of keywords supported by the playback device; and

responsive to the determining that the second input sound data stream includes voice input data comprising a keyword, causing the playback device or a

system comprising the playback device to perform a command corresponding to the keyword.

9. The method according to claim 8 , further comprising:

storing historical data in the data storage, the historical data including detected events and any associated commands; and

analyzing the historical data to adjust the given time period associated with the input detection window.

10. The method according to claim 9 , wherein analyzing the historical data comprises:

determining a frequency of the associated commands and a time period, relative to a time of the detected event, during which the associated commands were received by the media playback system; and

setting the given time period based on the frequency and the time period.

11. The method according to claim 9 , wherein the given time period is associated with a user account of the playback device or a system comprising the playback device.

12. The method according to claim 8 , wherein outside of the input detection window, the second input sound data stream is not analyzed.

13. The method according to claim 8 , wherein the playback device comprises a network interface, and the method further comprises:

transmitting, via the network interface and during the input detection window, at least part of the second input sound data stream to a remote server for analysis;

receiving data including a remote command from the remote server, the remote command being supported by the playback device; and

causing the playback device or a system comprising the playback device to perform the remote command.

14. The method according to claim 8 , wherein the analyzing the second input data stream comprises determining a keyword by at least one of:

natural language processing to determine an intent, based on an analysis of the keyword in the input sound data stream; and

pattern-matching based on a predefined library of keywords and associated keywords.

15. A non-transitory computer-readable medium having instructions stored thereon that are executable by one or more processors to cause a playback device to perform functions, the playback device comprising at least one microphone configured to detect sound, the functions comprising:

detecting a first input sound data stream comprising a wake word and a voice input; performing an action based on the voice input, wherein the action comprises initiating

playback of a playback queue;

while playing back the playback queue, detecting an event associated with the playback device or a system comprising the playback device, wherein the event comprises an indication of a track change associated with the playback queue, wherein the indication corresponds to a user input to change a track via a controller device

opening, responsive to the detecting the event comprising the indication of the track change, an input detection window for a given time period; and

during the given time period:

receiving a second input sound data stream representing the sound detected by the at least one microphone;

analyzing the second input sound data stream for a plurality of keywords supported by the playback device;

determining based on the analysis, that the second input sound data stream includes voice input data comprising a keyword; wherein the keyword is one of the plurality of keywords supported by the playback device; and

responsive to the determining that the second input sound data stream includes voice input data comprising a keyword, causing the playback device or a system comprising the playback device to perform a command corresponding to the keyword.