公开(公告)号：US20210166720A1

公开(公告)日：2021-06-03

申请号：US17023880

申请日：2020-09-17

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Changwoo HAN ,  Minkyu SHIN ,  Jonguk YOO ,  Dokyun LEE ,  Kangseok CHOI

IPC: G10L25/51 ,  G10L25/30 ,  G10L21/0272 ,  G06N3/08

Abstract: A method, performed by an electronic device, of identifying location information of an external includes: obtaining map information including location information for each time interval of a mobile device based on the mobile device moving while generating noise near the external device; obtaining audio signal information about an audio signal including the noise generated by the mobile device, the audio signal being collected by a microphone of the external device; identifying, from the audio signal information, a time point at which a noise level of the noise generated by the mobile device is highest; obtaining, from the map information, location information of the mobile device corresponding to the identified time point; and identifying the location information of the external device based on the obtained location information of the mobile device.

公开(公告)号：US20240274128A1

公开(公告)日：2024-08-15

申请号：US18420338

申请日：2024-01-23

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Changwoo HAN ,  Dokyun LEE ,  Jungwook HWANG ,  Jaeyoung ROH ,  Jonguk YOO ,  Youngmoon JUNG ,  Youngo HAN

IPC: G10L15/20 ,  G06F3/16 ,  G10L15/08 ,  G10L15/22

CPC classification number: G10L15/20 ,  G06F3/167 ,  G10L15/083 ,  G10L15/22 ,  G10L2015/088 ,  G10L2015/223

Abstract: An electronic device includes a microphone; at least one memory storing a wake-up word detection model; and at least one processor configured to: obtain a sound signal received through the microphone, input the sound signal into the wake-up word detection model, obtain, as an output of the wake-up word detection model, one or more first probability scores corresponding to one or more sections of the sound signal, wherein each first probability score of the one or more first probability scores represents a probability that a corresponding section of the one or more sections of the sound signal corresponds to a wake-up word, identify a first section of the sound signal, among the one or more sections of the sound signal, that corresponds to a first probability score, among the one or more first probability scores, that exceeds a first threshold value, and based on identifying a predetermined acoustic signal in the sound signal, reduce the first threshold value.

公开(公告)号：US20220035514A1

公开(公告)日：2022-02-03

申请号：US17278977

申请日：2019-10-11

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Minkyu SHIN ,  Sangyoon KIM ,  Dokyun LEE ,  Changwoo HAN ,  Jonguk YOO ,  Jaewon LEE

IPC: G06F3/0484 ,  G06F3/0488 ,  G06K9/00 ,  G10L15/26

Abstract: Provided are an electronic device capable of providing text information corresponding to a user voice through a user interface and a method of controlling the electronic device. Specifically, an electronic device according to the present disclosure, when an image including at least one object is obtained, analyzes the image to identify the at least one object included in the image, and when a user voice is received, performs voice recognition on the user voice to obtain text information corresponding to the user voice, then identifies an object corresponding to the user voice among the at least one object included in the image, and displays a memo user interface (UI) including text information on an area corresponding to the object identified as corresponding to the user voice among areas on a display.