US 11,727,936 B2
Voice detection optimization based on selected voice assistant service
Connor Kristopher Smith, New Hudson, MI (US); Kurt Thomas Soto, Ventura, CA (US); and Charles Conor Sleith, Waltham, MA (US)
Assigned to Sonos, Inc., Santa Barbara, CA (US)
Filed by Sonos, Inc., Santa Barbara, CA (US)
Filed on Jun. 7, 2021, as Appl. No. 17/303,735.
Application 17/303,735 is a continuation of application No. 16/798,967, filed on Feb. 24, 2020, granted, now 11,031,014.
Application 16/798,967 is a continuation of application No. 16/434,426, filed on Jun. 7, 2019, granted, now 10,573,321, issued on Feb. 25, 2020.
Application 16/434,426 is a continuation of application No. 16/141,875, filed on Sep. 25, 2018, granted, now 10,811,015, issued on Oct. 20, 2020.
Prior Publication US 2021/0295848 A1, Sep. 23, 2021
This patent is subject to a terminal disclaimer.
Int. Cl. G10L 15/30 (2013.01); G10L 15/08 (2006.01); G10L 15/22 (2006.01); H04R 1/40 (2006.01); H04R 3/00 (2006.01)
CPC G10L 15/30 (2013.01) [G10L 15/08 (2013.01); G10L 15/22 (2013.01); H04R 1/406 (2013.01); H04R 3/005 (2013.01); G10L 2015/088 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A playback device comprising:
a housing;
a plurality of microphones disposed within the housing;
a network interface disposed within the housing;
one or more processors disposed within the housing; and
data storage disposed within the housing, the data storage having instructions stored therein that, when executed by the one or more processors, cause the playback device to perform operations comprising:
capturing a first audio input via a first set of microphones from the plurality of microphones;
analyzing the first audio input using a first wake-word engine on the playback device to detect a first wake word associated with a first voice assistant service (VAS);
receiving an indication of a use selection to associate the playback device with a second VAS in place of the first VAS;
after receiving the indication, capturing a second audio input via a second set of microphones selected from the plurality of microphones, wherein the second set of microphones is a subset of the first set of microphones; and
analyzing the second audio input using a second wake-word engine on the playback device to detect a second wake word associated with the second VAS, the second wake-word engine being different from the first wake-word engine and the second wake word being different from the first wake word.