US 11,721,334 B2
Method and apparatus for controlling device located a distance away from a user
Jong Hoon Chae, Seoul (KR); Minook Kim, Seoul (KR); Yongchul Park, Seoul (KR); Sungmin Han, Seoul (KR); Siyoung Yang, Seoul (KR); Sangki Kim, Seoul (KR); and Juyeong Jang, Seoul (KR)
Assigned to LG ELECTRONICS INC., Seoul (KR)
Filed by LG ELECTRONICS INC., Seoul (KR)
Filed on Mar. 5, 2020, as Appl. No. 16/810,013.
Claims priority of application No. 10-2019-0159875 (KR), filed on Dec. 4, 2019.
Prior Publication US 2021/0174796 A1, Jun. 10, 2021
Int. Cl. G10L 15/22 (2006.01); G10L 15/02 (2006.01); G10L 15/16 (2006.01); G10L 25/90 (2013.01); G10L 25/84 (2013.01); G10L 25/18 (2013.01); G06N 3/04 (2023.01); G10L 15/187 (2013.01)
CPC G10L 15/22 (2013.01) [G06N 3/04 (2013.01); G10L 15/02 (2013.01); G10L 15/16 (2013.01); G10L 15/187 (2013.01); G10L 25/18 (2013.01); G10L 25/84 (2013.01); G10L 25/90 (2013.01); G10L 2015/223 (2013.01)] 19 Claims
OG exemplary drawing
 
1. A method for controlling a device according to a user's calling, the method comprising:
receiving a user utterance collected by a plurality of electronic devices;
measuring a distance between the user and the plurality of electronic devices;
extracting a first electronic device and a second electronic device configured to perform an operation corresponding to the user utterance among the plurality of electronic devices;
analyzing a style of the user utterance based on a user speech feature extracted from the user utterance through a speech recognition neural network;
in response to the style of the user utterance corresponding to a pre-stored average utterance style of the user and the first electronic device being located a shorter distance away from the user than the second electronic device, selecting the first electronic device as an individual target device and controlling an operation of the first electronic device based on the user utterance while the second electronic device does not respond to the user utterance; and
in response to the style of the user utterance being different than the pre-stored average utterance style of the user and the second electronic device being located a farther distance away from the user than the first electronic device, selecting the second electronic device as the individual target device and controlling an operation of the second electronic device based on the user utterance while the first electronic device does not respond to the user utterance,
wherein the pre-stored average utterance style of the user is based on a plurality of spoken utterances of the user, and
wherein the method further comprises:
comparing a pitch of the style of the user utterance with a pitch of the pre-stored average utterance style; and
in response to the pitch of the style of the user utterance being higher than the pitch of the pre-stored average utterance style, selecting the at least one electronic device, which is located farther away from the user than one or more other devices among the at least one electronic device, as the individual target device.