公开(公告)号：US20220270615A1

公开(公告)日：2022-08-25

申请号：US17741087

申请日：2022-05-10

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Cheheung KIM ,  Sungchan Kang ,  Sangha Park ,  Yongseop Yoon ,  Choongho Rhee

IPC: G10L17/14 ,  G01H13/00 ,  G10L17/02 ,  G10L17/04 ,  G10L17/20

Abstract: Provided are a method and device for recognizing a speaker by using a resonator. The method of recognizing the speaker includes receiving a plurality of electrical signals corresponding to a speech of the speaker from a plurality of resonators having different resonance bands; obtaining a difference of magnitudes of the plurality of electrical signals; and recognizing the speaker based on the difference of magnitudes of the plurality of electrical signals.

公开(公告)号：US20220240005A1

公开(公告)日：2022-07-28

申请号：US17717920

申请日：2022-04-11

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Cheheung KIM ,  Sungchan KANG ,  Hyeokki HONG ,  Hyunwook KANG ,  Yongseop YOON ,  Choongho RHEE

IPC: H04R1/32 ,  H04R3/00 ,  H04R17/10

Abstract: A compact directional acoustic sensor having an improved signal-to-noise ratio is disclosed. The disclosed directional acoustic sensor includes a first sensing device configured to generate different output gains based on different input directions of external energy, and configured to generate at least one first output signal having a first polarity based on external energy received from an input direction; a second sensing device configured to generate different output gains based on different input directions of external energy, and configured to generate at least one second output signal having a second polarity, that is different than the first polarity, based on the external energy received from the input direction; and at least one signal processor configured to generate at least one final output signal based on the at least one first output signal and the at least one second output signal.

公开(公告)号：US20220099828A1

公开(公告)日：2022-03-31

申请号：US17187097

申请日：2021-02-26

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Sungchan KANG ,  Cheheung KIM ,  Daehyuk SON

IPC: G01S15/08

Abstract: Provided is a distance measurement system, including: at least one sound source configured to generate an acoustic signal; an acoustic sensor including a plurality of directional acoustic sensors arranged to have directionalities different from one another; and at least one processor configured to: obtain a directionality of the acoustic signal in a particular direction based on at least one of a sum of output signals of the plurality of directional acoustic sensors or a difference between the output signals of the plurality of directional acoustic sensors, the at least one of the sum or the difference being based on applying a weight to at least one of the output signals; and determine a distance between the acoustic sensor and a reflection surface based on a time for the acoustic signal to arrive at the acoustic sensor in the particular direction after being generated and then reflected from the reflection surface.

公开(公告)号：US20220086570A1

公开(公告)日：2022-03-17

申请号：US17182911

申请日：2021-02-23

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Hyunwook KANG ,  Sungchan KANG ,  Cheheung KIM ,  Choongho RHEE ,  Hyeokki HONG

IPC: H04R17/10 ,  H01L27/20 ,  H01L41/113 ,  H04R17/02

Abstract: Provided is a sensor interface including a first cantilever beam bundle including at least one resonator and a first output terminal, a second cantilever beam bundle including at least one resonator and a second output terminal, and a differential amplifier including a first input terminal electrically connected to the first output terminal of the first cantilever beam bundle and a second input terminal electrically connected to the second output terminal of the second cantilever beam bundle.

公开(公告)号：US20210329395A1

公开(公告)日：2021-10-21

申请号：US17320988

申请日：2021-05-14

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Cheheung KIM ,  Sungchan Kang ,  Yongseop Yoon ,  Choongho Rhee ,  Sangha Park ,  Hyeokki Hong

IPC: H04S7/00 ,  H04R5/04 ,  G10L21/0216 ,  H04R1/32 ,  B60K35/00 ,  G06F3/16 ,  H04R1/40 ,  H04R1/24

Abstract: Provided are a directional acoustic sensor that detects a direction of sound, a method of detecting a direction of sound, and an electronic device including the directional acoustic sensor. The directional acoustic sensor includes a sound inlet through which a sound is received, a sound outlet through which the sound received through the sound inlet is output, and a plurality of vibration bodies arranged between the sound inlet and the sound outlet, in which one or more of the plurality of vibration bodies selectively react to the sound received by the sound inlet according to a direction of the received sound.

公开(公告)号：US20210210087A1

公开(公告)日：2021-07-08

申请号：US16920894

申请日：2020-07-06

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Cheheung KIM ,  Jaehyung Jang ,  Hyeokki Hong

IPC: G10L15/22 ,  G10L15/30

Abstract: Disclosed are a voice recognition system and a display device using the same. The disclosed voice recognition system includes a plate structure, a vibration sensor, and a voice recognition device. The plate structure vibrates based on propagation of a voice wave generated from a user, and the vibration sensor is provided in contact with the plate structure to detect the vibration of the plate structure. The voice recognition device recognizes voice of the user by receiving a signal output from the vibration sensor.

公开(公告)号：US20200242454A1

公开(公告)日：2020-07-30

申请号：US16557182

申请日：2019-08-30

Applicant: Samsung Electronics Co., Ltd.

Inventor： Sungho KIM ,  Cheheung KIM ,  Jaeho LEE

IPC: G06N3/063 ,  G06F7/57

Abstract: A neural network apparatus that is configured to process an operation includes neural network circuitry configured to receive a first input of an n-bit activation, store a second input of an m-bit weight, perform a determination whether to perform an operation on an ith bit of the first input and a jth bit of the second input, output an operation value of an operation performed on the ith bit of the first input and the jth bit of the second input based on the determination, and produce an operation value of the operation based on the determination.

公开(公告)号：US20190156837A1

公开(公告)日：2019-05-23

申请号：US16134529

申请日：2018-09-18

Applicant: SAMSUNG ELECTRONICS CO., LTD. ,  SEOUL NATIONAL UNIVERSITY R&DB FOUNDATION

Inventor： Sangha PARK ,  Namsoo KIM ,  Hyungyong KIM ,  Sungchan KANG ,  Cheheung KIM ,  Yongseop YOON ,  Choongho RHEE ,  Hyeokki HONG

IPC: G10L17/18 ,  G06N3/08 ,  G06N3/04 ,  G10L17/02 ,  G10L17/06

Abstract: Provided are a neural network device and a method of operation thereof. The neural network device for speaker recognition may include: a memory configured to store one or more instructions; and a processor configured to generate a trained second neural network by training a first neural network, for separating a mixed voice signal into individual voice signals by executing the one or more instructions, generate a second neural network by adding at least one layer to the trained first neural network, and generate a trained second neural network by training the second neural network, for separating the mixed voice signal into the individual voice signals and for recognizing a speaker of each of the individual voice signals.

公开(公告)号：US20190122690A1

公开(公告)日：2019-04-25

申请号：US15994171

申请日：2018-05-31

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Cheheung KIM ,  Sungchan KANG ,  Sangha PARK ,  Yongseop YOON ,  Choongho RHEE ,  Hyeokki HONG

IPC: G10L21/0388 ,  G10L21/0232 ,  H03G5/16

Abstract: Sound signal processing apparatuses and methods of operating the same are provided. The sound signal processing apparatus includes: a band separator configured to separate sound signals into frequency bands; an adder configured to add sound signals; and a signal processor that is arranged between the band separator and the adder and comprises a plurality of signal processing blocks. The band separator includes elements for separating the sound signals into frequency bands, and the elements correspond one to one to the signal processing blocks.

公开(公告)号：US20180138886A1

公开(公告)日：2018-05-17

申请号：US15477203

申请日：2017-04-03

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Yongseop YOON ,  Sungchan KANG ,  Cheheung KIM ,  Sangha PARK ,  Choongho RHEE

IPC: H03H9/02 ,  H03H9/17 ,  H01L41/047

CPC classification number: H03H9/02244 ,  G01H1/00 ,  G01H11/08 ,  H01L41/047 ,  H01L41/0477 ,  H01L41/1136 ,  H03H9/17 ,  H03H2009/155

Abstract: A piezoelectric micromechanical resonator includes a supporting beam including a fixed edge that is fixed to a supporting member and a free edge opposite the fixed edge, a piezoelectric sensor including an edge attached to the supporting member, the piezoelectric sensor further including a lower electrode, a piezoelectric unit, and an upper electrode sequentially stacked on a surface of the supporting beam, and a lumped mass provided on the surface of the supporting beam at a side of the supporting beam including the free edge, the upper electrode having a Young's modulus smaller than a Young's modulus of the lower electrode.