US 11,715,464 B2
Using augmentation to create natural language models
Thomas Robert Nickson, Campbell, CA (US); Keith Scott Brisson, San Francisco, CA (US); Eric Gregory, Larkspur, CA (US); Thomas B. Gunter, Oxford (GB); and Arthur A. Van Hoff, Menlo Park, CA (US)
Assigned to Apple Inc., Cupertino, CA (US)
Filed by Apple Inc., Cupertino, CA (US)
Filed on Jul. 2, 2021, as Appl. No. 17/366,519.
Claims priority of provisional application 63/078,280, filed on Sep. 14, 2020.
Prior Publication US 2022/0084511 A1, Mar. 17, 2022
Int. Cl. G10L 15/183 (2013.01); G10L 15/06 (2013.01)
CPC G10L 15/183 (2013.01) [G10L 15/063 (2013.01); G10L 2015/0635 (2013.01)] 42 Claims
OG exemplary drawing
 
1. An electronic device comprising:
one or more processors;
a memory; and
one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs including instructions for:
receiving an utterance;
determining one or more words of the utterance unrecognized by a first natural language model associated with a first application;
marking the one or more unrecognized words as a reference;
determining whether a parameter of a second natural language model associated with a second application satisfies a requirement of the reference;
in accordance with a determination that the parameter of the second natural language model associated with the second application satisfies the requirement of the reference, storing the relationship between the reference and the parameter in the first natural language model associated with the first application.