公开(公告)号：US20190244612A1

公开(公告)日：2019-08-08

申请号：US16265237

申请日：2019-02-01

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Youngho HAN ,  Keunseok CHO ,  Jaeyoung ROH ,  Namhoon KIM ,  Chiyoun PARK ,  Jongyoub RYU

IPC: G10L15/22 ,  G10L15/02 ,  G10L25/84 ,  G10L15/187

CPC classification number: G10L15/22 ,  G10L15/02 ,  G10L15/187 ,  G10L25/84 ,  G10L2015/025

Abstract: A method of processing a speech signal for speaker recognition in an electronic apparatus includes: obtaining a speech signal of a first user; extracting a speech feature comprising a feature value from the speech signal; comparing the speech feature extracted from the speech signal of the first user with a predetermined reference value; selecting a first user feature that corresponds to the speech feature of the first user compared with the reference value; generating a recommended phrase used for speaker recognition based on the first user feature; and outputting the recommended phrase.

公开(公告)号：US20200175993A1

公开(公告)日：2020-06-04

申请号：US16700264

申请日：2019-12-02

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Keunseok CHO ,  Jaeyoung ROH ,  Donghan JANG ,  Jiwon HYUNG ,  Jaewon LEE

IPC: G10L17/24 ,  G10L17/06 ,  G10L15/02 ,  G10L15/04 ,  G06F21/32

Abstract: A method and apparatus for authenticating a user based on an utterance input includes obtaining an input audio signal based on the utterance input of the user; obtaining, from the input audio signal, at least one audio signal of an utterance section and at least one audio signal of a non-utterance section; generating environment information indicating an environment in which the utterance input is received, based on the at least one audio signal of the non-utterance section; obtaining a result of a comparison between the generated environment information and registration environment information indicating an environment in which a registration utterance input corresponding to a previously registered registration audio signal corresponding to the user is received; adjusting an authentication criterion for authenticating the user based on the result of the comparison; and authenticating the user based on the adjusted authentication criterion and the input audio signal.

公开(公告)号：US20200168230A1

公开(公告)日：2020-05-28

申请号：US16692696

申请日：2019-11-22

Applicant: Samsung Electronics Co., Ltd.

Inventor： Jaeyoung ROH ,  Keunseok CHO ,  Jiwon HYUNG ,  Donghan JANG ,  Jaewon LEE

IPC: G10L17/00 ,  G10L17/18 ,  G10L17/04 ,  G10L17/26 ,  G10L15/02

Abstract: A method and apparatus for processing voice data of a speech received from a speaker are provided. The method includes extracting a speaker feature vector from the voice data of the speech received from a speaker, generating a speaker feature map by positioning the extracted speaker feature vector at a specific position on a multi-dimensional vector space, forming a plurality of clusters indicating features of voices of a plurality of speakers by grouping at least one speaker feature vector positioned on the speaker feature map, and classifying the plurality of speakers according to the plurality of clusters.

公开(公告)号：US20250155978A1

公开(公告)日：2025-05-15

申请号：US19025027

申请日：2025-01-16

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Dongseop LEE ,  Jiwon HYUNG ,  Hakjung KIM ,  Daniel Dongyuel LEE ,  Yusun SON ,  Dojun YANG ,  Keunseok CHO

IPC: G06F3/01 ,  A61B5/00 ,  A61B5/276

Abstract: A biosignal detection apparatus includes: a sensor unit including a plurality of electrodes configured to obtain a biosignal; memory storing one or more instructions; and one or more processors configured to execute the one or more instructions to: determine a time during which arbitrary electrodes of the plurality of electrodes obtain the biosignal, determine a variability of the biosignal obtained by the arbitrary electrodes, and based on the time during which the arbitrary electrodes obtain the biosignal and the variability of the obtained biosignal satisfying a predetermined reference, determine an arrangement of the arbitrary electrodes and learn the arrangement of the arbitrary electrodes.

公开(公告)号：US20230185381A1

公开(公告)日：2023-06-15

申请号：US18075900

申请日：2022-12-06

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Keunseok CHO ,  Yusun SON ,  Jiwon HYUNG ,  Dojun YANG

IPC: G06F3/01 ,  G06F1/16

CPC classification number: G06F3/017 ,  G06F3/015 ,  G06F1/163

Abstract: Provided is a method and device for recognizing, by a wearable device, a gesture. The method of recognizing, by a wearable device, a user gesture includes identifying a trigger gesture of the wearable device, obtaining an electromyographic signal set from a plurality of electromyography sensors, based on a movement of a user's body for the identified trigger gesture, obtaining at least one output value by using one or more electromyographic signals from among the obtained electromyographic signal set, as an input to a gesture recognition model, selecting, based on the wearable device being in a standby mode, at least one active electromyography sensor to recognize the user gesture, based on the obtained output value, activating the selected active electromyography sensor and recognizing the user gesture by using the activated at least one active electromyography sensor based on the wearable device being in standby mode.

公开(公告)号：US20220392456A1

公开(公告)日：2022-12-08

申请号：US17888051

申请日：2022-08-15

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Keunseok CHO ,  Jaeyoung ROH ,  Donghan JANG ,  Jiwon HYUNG ,  Jaewon LEE

IPC: G10L17/24 ,  G10L17/06 ,  G06F21/32 ,  G10L15/04 ,  G10L15/02

Abstract: A method and apparatus for authenticating a user based on an utterance input includes obtaining an input audio signal based on the utterance input of the user; obtaining, from the input audio signal, at least one audio signal of an utterance section and at least one audio signal of a non-utterance section; generating environment information indicating an environment in which the utterance input is received, based on the at least one audio signal of the non-utterance section; obtaining a result of a comparison between the generated environment information and registration environment information indicating an environment in which a registration utterance input corresponding to a previously registered registration audio signal corresponding to the user is received; adjusting an authentication criterion for authenticating the user based on the result of the comparison; and authenticating the user based on the adjusted authentication criterion and the input audio signal.