US 12,033,632 B2
Context-based device arbitration
Joseph White, San Francisco, CA (US); Ravi Kiran Rachakonda, San Jose, CA (US); Vinodth Kumar Mohanam, Santa Clara, CA (US); Lalithkumar Rajendran, Austin, TX (US); Deepak Uttam Shah, Milpitas, CA (US); Maziyar Khorasani, San Francisco, CA (US); and Venkata Snehith Cherukuri, San Jose, CA (US)
Assigned to Amazon Technologies, Inc., Seattle, WA (US)
Filed by Amazon Technologies, Inc., Seattle, WA (US)
Filed on Mar. 22, 2022, as Appl. No. 17/701,387.
Application 17/701,387 is a continuation of application No. 16/752,262, filed on Jan. 24, 2020, granted, now 11,289,087.
Application 16/752,262 is a continuation of application No. 15/691,460, filed on Aug. 30, 2017, granted, now 10,546,583, issued on Jan. 28, 2020.
Prior Publication US 2022/0215837 A1, Jul. 7, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G10L 15/00 (2013.01); G10L 15/18 (2013.01); G10L 15/22 (2006.01); G10L 15/28 (2013.01); G10L 25/84 (2013.01)
CPC G10L 15/22 (2013.01) [G10L 15/1815 (2013.01); G10L 15/28 (2013.01); G10L 25/84 (2013.01); G10L 2015/223 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A device comprising:
one or more processors; and
non-transitory computer-readable media storing instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising:
determining that audio data generated from audio received at the device includes a wake word;
receiving first data from a second device, the first data indicating that the second device detected the wake word;
determining, based at least in part on the first data, that the device is to be used to perform a machine response;
determining that the audio data includes speech input following the wake word;
determining the machine response to the speech input; and
causing the machine response to be performed.