US 11,954,405 B2
Zero latency digital assistant
William F. Stasior, Los Altos, CA (US); David A. Carson, San Francisco, CA (US); Rohit Dasari, San Francisco, CA (US); and Yoon Kim, Los Altos, CA (US)
Assigned to Apple Inc., Cupertino, CA (US)
Filed by Apple Inc., Cupertino, CA (US)
Filed on Nov. 7, 2022, as Appl. No. 17/982,337.
Application 17/982,337 is a continuation of application No. 17/403,674, filed on Aug. 16, 2021, granted, now 11,550,542.
Application 17/403,674 is a continuation of application No. 16/909,852, filed on Jun. 23, 2020, granted, now 11,126,400, issued on Sep. 21, 2021.
Application 16/909,852 is a continuation of application No. 15/147,726, filed on May 5, 2016, granted, now 10,747,498, issued on Aug. 18, 2020.
Claims priority of provisional application 62/215,608, filed on Sep. 8, 2015.
Prior Publication US 2023/0057442 A1, Feb. 23, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 3/16 (2006.01); G06F 3/038 (2013.01); G06F 3/0481 (2022.01); G06F 3/06 (2006.01); G10L 15/08 (2006.01); G10L 15/22 (2006.01); G10L 15/28 (2013.01); G10L 15/32 (2013.01)
CPC G06F 3/167 (2013.01) [G06F 3/038 (2013.01); G06F 3/0481 (2013.01); G06F 3/0604 (2013.01); G06F 3/0656 (2013.01); G06F 3/0673 (2013.01); G10L 15/22 (2013.01); G10L 15/32 (2013.01); G10L 2015/088 (2013.01); G10L 2015/223 (2013.01); G10L 15/285 (2013.01); H04M 2201/40 (2013.01); H04M 2250/74 (2013.01)] 39 Claims
OG exemplary drawing
 
1. A non-transitory computer-readable storage medium storing one or more programs, the one or more programs comprising instructions, which when executed by one or more processors of an electronic device with a microphone, cause the device to:
while a main processor is in a low-power mode:
capture audio input from the microphone;
write, using a low-power processor, the captured audio input to a memory buffer; and
determine, using the low-power processor, whether the buffered audio input satisfies a set of criteria, wherein determining whether the buffered audio input satisfies the set of criteria includes:
determining whether a first portion of the buffered audio input includes a trigger phrase, wherein a first criterion of the set of criteria is satisfied when the first portion of the buffered audio input includes the trigger phrase; and
determining, by comparing speech characteristics of the buffered audio input to a set of known characteristics for an authorized user, whether the trigger phrase was spoken by the authorized user, wherein a second criterion of the set of criteria is satisfied when the first portion of the buffered audio input is spoken by the authorized user; and
in accordance with a determination that the buffered audio input satisfies the set of criteria:
cause the main processor to exit the low-power mode; and
after causing the main processor to exit the low-power mode:
identify, using the main processor, a computing task based on a second portion of the buffered audio input; and
execute, using the main processor, the identified computing task; and
in accordance with a determination that the buffered audio input does not satisfy the set of criteria, forgo causing the main processor to exit the low-power mode, identifying the computing task, and executing the computing task.