US 12,249,316 B1
Speech recognition services
Gregory Michael Hart, Mercer Island, WA (US); John Daniel Thimsen, Seattle, WA (US); Allan Timothy Lindsay, Seattle, WA (US); Scott Ian Blanksteen, Issaquah, WA (US); Peter Paul Henri Carbon, Bellevue, WA (US); Vikram Kumar Gundeti, Bellevue, WA (US); and Frederic Johan Georges Deramat, Bellevue, WA (US)
Assigned to Amazon Technologies, Inc., Seattle, WA (US)
Filed by Amazon Technologies, Inc., Seattle, WA (US)
Filed on Oct. 10, 2022, as Appl. No. 17/962,791.
Application 17/962,791 is a continuation of application No. 16/806,516, filed on Mar. 2, 2020, granted, now 11,468,889.
Application 16/806,516 is a continuation of application No. 15/896,495, filed on Feb. 14, 2018, granted, now 10,580,408, issued on Mar. 3, 2020.
Application 15/896,495 is a continuation of application No. 15/243,288, filed on Aug. 22, 2016, abandoned.
Application 15/243,288 is a continuation of application No. 13/842,804, filed on Mar. 15, 2013, granted, now 9,424,840, issued on Aug. 23, 2016.
Claims priority of provisional application 61/696,055, filed on Aug. 31, 2012.
Int. Cl. G10L 15/22 (2006.01); G06F 3/16 (2006.01); G10L 15/00 (2013.01); G10L 21/06 (2013.01); G10L 15/18 (2013.01)
CPC G10L 15/00 (2013.01) [G06F 3/167 (2013.01); G10L 15/22 (2013.01); G10L 21/06 (2013.01); G10L 15/1815 (2013.01); G10L 2015/223 (2013.01); G10L 2015/225 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A system comprising:
one or more processors; and
one or more computer-readable media storing computer-executable instructions that, when executed by the one or more processors, cause the one or more processors to perform acts comprising:
receiving a first audio signal that represents a request from a user in an environment;
receiving an indication of an identifier associated with the user;
determining context data associated with the identifier of the user, wherein the context data is based at least in part on prior requests of the user;
performing speech recognition on the first audio signal to generate a speech-recognition result;
analyzing the speech-recognition result and the context data to determine a first domain and a first intent associated with the first domain, the first domain comprising a first set of related intents;
analyzing the speech-recognition result and the context data to determine a second domain and a second intent associated with the second domain, the second domain comprising a second set of related intents;
generating a second audio signal that represents a query regarding whether the request corresponds to the first domain or the second; and
sending the second audio signal to an electronic device.