US 11,670,294 B2
Method of generating wakeup model and electronic device therefor
Jaehoon Jeong, Gyeonggi-do (KR); Sukanya Sonowal, Gyeonggi-do (KR); Daewoong Song, Gyeonggi-do (KR); Shinjae Kang, Gyeonggi-do (KR); Junseok Oh, Gyeonggi-do (KR); and Sangho Lee, Gyeonggi-do (KR)
Assigned to Samsung Electronics Co., Ltd., Suwon-si (KR)
Filed by Samsung Electronics Co., Ltd., Gyeonggi-do (KR)
Filed on Oct. 12, 2020, as Appl. No. 17/67,903.
Prior Publication US 2021/0110825 A1, Apr. 15, 2021
Int. Cl. G10L 15/22 (2006.01); G10L 15/183 (2013.01)
CPC G10L 15/22 (2013.01) [G10L 2015/223 (2013.01)] 20 Claims
OG exemplary drawing
 
1. An electronic device comprising:
a microphone;
a communication circuit;
at least one processor operatively connected to the microphone and the communication circuit; and
a memory operatively connected to the at least one processor,
wherein the memory stores one or more instructions that, when executed, cause the at least one processor to:
obtain first audio data at the electronic device through the communication circuit, wherein the first audio data is based on a user utterance recorded by an external electronic device and the user utterance includes a wakeup word used for generating a previous wakeup model by the external electronic device, the previous wakeup model used to verify the wakeup word at the external electronic device;
convert the first audio data into second audio data, using a first transfer function of the microphone of the electronic device, wherein the second audio data estimates a voice signal that would be detected by the microphone of the electronic device if the user utterance including the wakeup word that was recorded at the external electronic device was uttered at the electronic device; and
generate a wakeup model at the electronic device, using the second audio data, the wakeup model configured to verify the wakeup word.