US 12,462,802 B2
Command keywords with input detection windowing
Connor Kristopher Smith, New Hudson, MI (US); and Matthew David Anderson, Santa Barbara, CA (US)
Assigned to Sonos, Inc., Goleta, CA (US)
Filed by Sonos, Inc., Santa Barbara, CA (US)
Filed on Jan. 11, 2024, as Appl. No. 18/410,407.
Application 18/410,407 is a continuation of application No. 18/048,945, filed on Oct. 24, 2022, granted, now 11,881,222.
Application 18/048,945 is a continuation of application No. 16/879,549, filed on May 20, 2020, granted, now 11,482,224, issued on Oct. 25, 2022.
Prior Publication US 2024/0212680 A1, Jun. 27, 2024
Int. Cl. G10L 15/00 (2013.01); G10L 15/08 (2006.01); G10L 15/22 (2006.01)
CPC G10L 15/22 (2013.01) [G10L 15/083 (2013.01); G10L 2015/088 (2013.01); G10L 2015/223 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A playback device comprising:
one or more microphones;
one or more processors; and
data storage having instructions stored thereon that, when executed by the one or more processors, cause the playback device to perform operations comprising:
detecting a first event, the first event being associated with the playback device or a media playback system comprising the playback device, wherein the first event is not based on sound data captured via the one or more microphones;
responsive to the first event detection, opening a first input detection window for a first time period, and while the first input detection window is open:
receiving a first input sound data stream from the one or more microphones;
detecting a first command keyword in the input sound data stream, wherein the first command keyword is one of a plurality of command keywords supported by the playback device; and
responsive to determining that (i) the first input sound data stream includes the first command keyword, and (ii) one or more first conditions associated with the first command keyword are satisfied, causing the media playback system to perform a first command corresponding to the first command keyword;
detecting a second event, the second event being associated with the playback device or the media playback system comprising the playback device, wherein the second event is not based on sound data captured via the one or more microphones;
responsive to the second event detection, opening a second input detection window for a second time period different than the first time period, and while the second input detection window is open:
receiving a second input sound data stream from the one or more microphones;
detecting a second command keyword in the input sound data stream, wherein the second command keyword is one of the plurality of command keywords supported by the playback device; and
responsive to determining that (i) the second input sound data stream includes the second command keyword, and (ii) one or more second conditions associated with the second command keyword are satisfied, causing the media playback system to perform a second command corresponding to the second command keyword.
 
7. A method comprising:
detecting a first event, the first event being associated with a playback device or a media playback system comprising the playback device, wherein the first event is not based on sound data captured via;
responsive to the first event detection, opening a first input detection window for a first time period, and while the first input detection window is open:
receiving a first input sound data stream from one or more microphones of the playback device;
detecting a first command keyword in the input sound data stream, wherein the first command keyword is one of a plurality of command keywords supported by the playback device; and
responsive to determining that the first input sound data stream includes the first command keyword, causing the media playback system to perform a first command corresponding to the first command keyword;
detecting a second event, the second event being associated with the playback device or the media playback system comprising the playback device, wherein the second event comprises an interaction with a user interface element associated with a second playback command, and wherein the user interface element does not relate to activating a voice input;
responsive to the second event detection, opening a second input detection window for a second time period different than the first time period, and while the second input detection window is open:
receiving a second input sound data stream from the one or more microphones;
detecting a second command keyword in the input sound data stream, wherein the second command keyword is one of the plurality of command keywords supported by the playback device; and
responsive to determining that the second input sound data stream includes the second command keyword, causing the media playback system to perform a second command corresponding to the second command keyword.