US 11,734,326 B2
Profile disambiguation
Rebecca Joy Lopdrup Miller, Seattle, WA (US); Dick Clarence Hardt, Seattle, WA (US); Joseph Jessup, Seattle, WA (US); Yu Bao, Issaquah, WA (US); Gonzalo Alvarez Barrio, Seattle, WA (US); and Liron Torres, Redmond, WA (US)
Assigned to Amazon Technologies, Inc., Seattle, WA (US)
Filed by Amazon Technologies, Inc., Seattle, WA (US)
Filed on Jul. 8, 2020, as Appl. No. 16/923,511.
Application 16/923,511 is a continuation of application No. 15/997,068, filed on Jun. 4, 2018, granted, now 10,733,222.
Prior Publication US 2020/0342011 A1, Oct. 29, 2020
This patent is subject to a terminal disclaimer.
Int. Cl. G10L 15/26 (2006.01); G06F 16/335 (2019.01); G10L 15/18 (2013.01); G10L 17/06 (2013.01)
CPC G06F 16/335 (2019.01) [G10L 15/18 (2013.01); G10L 15/26 (2013.01); G10L 17/06 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
receiving, from a first device that is associated with a first profile, first data;
determining that the first data is associated with a second profile that is associated with a second device different from the first device;
based at least in part on the first data being associated with the second profile, determining to temporarily associate the second profile with the first device;
storing second data associating the second profile with the first device;
receiving input audio data corresponding to an utterance detected by the first device;
determining, using the second data, that the second first profile is associated with the first device;
using the second profile to determine the utterance was spoken by a user associated with the second profile;
performing speech processing using the input audio data to determine a command to be executed based at least in part on the second profile; and
causing the command to be executed.