公开(公告)号：US20200021954A1

公开(公告)日：2020-01-16

申请号：US16577811

申请日：2019-09-20

Applicant: LG ELECTRONICS INC.

Inventor： Kyuho LEE ,  Jaewoong JEONG ,  Youngman KIM ,  Sangjun OH ,  Seunghyun HWANG

IPC: H04W4/16 ,  H04W64/00 ,  H04W60/00 ,  H04L12/28

Abstract: An intelligent device controlling method, a mobile terminal, and a computing device are provided. A mobile terminal for controlling intelligently a device according to an embodiment of the present disclosure receives a call for a call connection, selects at least one control target device to control an operation while the call is connected, based on a location of the mobile terminal, selects a control item of the at least one control target device using a plurality of pre-learned control methods, and controls the control item for the at least one control target device in a state where the call is connected. Accordingly, it is possible to improve a call environment by controlling an operation of a device around a smart phone at the time of a call connection of the smart phone. At least one of a mobile terminal and an intelligent computing device of the present disclosure is associated with an artificial intelligence module, an unmmanned aerial vehicle (UAV), a robot, an augmented reality (AR) device, a virtual reality (VR) device, and a device related to a 5G service.

公开(公告)号：US20240223707A1

公开(公告)日：2024-07-04

申请号：US17921301

申请日：2022-06-07

Applicant: LG ELECTRONICS INC.

Inventor： Jaepil SEO ,  Sungmoon CHO ,  Sangjun OH ,  Hyeonsik CHOI

IPC: H04M3/56

CPC classification number: H04M3/568 ,  H04M3/567

Abstract: A far-end terminal including a communication interface configured to wirelessly communicate with a near-end terminal for performing a video conference between the far-end terminal and the near-terminal, a camera configured to capture a region in front of the far-end terminal including a plurality of counterpart speakers, a display configured to display the plurality of counterpart speakers captured through the camera and to display an image of a speaker at the near-end terminal, and a processor configured to receive focusing mode setting information from the near-end terminal indicating an operation mode of the near-end terminal is a wide focusing mode, in response to the focusing mode setting information indicating the operation mode is the wide focusing mode, obtain an angle range corresponding to a narrower partial region of an entire region including the plurality of counterpart speakers at the far-end terminal, perform selective audio focusing on a received voice within the obtained angle range to selectively increase a gain of the received voice and to selectively decrease a gain of other received voices outside the obtained angle range, and transmit audio, which is a result of performing the beamforming, to the near-end terminal

公开(公告)号：US20230386491A1

公开(公告)日：2023-11-30

申请号：US17820220

申请日：2022-08-16

Applicant: LG ELECTRONICS INC.

Inventor： Jaepil SEO ,  Sungmoon CHO ,  Sangjun OH ,  Hyeonsik CHOI

IPC: G10L21/0216

CPC classification number: G10L21/0216 ,  G10L2021/02166

Abstract: Voice output of a specific speaker is controlled using beamforming according to a video zooming magnification. By simultaneously performing adaptive beamforming and fixed beamforming, it is possible to reinforce voice output of the specific speaker.

公开(公告)号：US20200092465A1

公开(公告)日：2020-03-19

申请号：US16584480

申请日：2019-09-26

Applicant: LG ELECTRONICS INC.

Inventor： Kyuho LEE ,  Jaewoong JEONG ,  Seunghyun HWANG ,  Youngman KIM ,  Sangjun OH

IPC: H04N5/232 ,  G06N3/08 ,  G06K9/62

Abstract: A method for editing an image based on artificial intelligence and an artificial intelligence device are disclosed. In the method for editing an image based on artificial intelligence, a recommended photographic composition is created by applying an image acquired by a camera to a pre-trained composition recommendation model, and the image is corrected based on the created recommended photographic composition, whereby it is possible to capture and edit an image at the same time without the trouble of correcting the image after capturing it. One or more of an artificial intelligence device of the present disclosure can be associated with artificial intelligence modules, drones (unmanned aerial vehicles (UAVs)), robots, augmented reality (AR) devices, virtual reality (VR) devices, devices related to 5G service, etc.

公开(公告)号：US20240061907A1

公开(公告)日：2024-02-22

申请号：US18062483

申请日：2022-12-06

Applicant: LG ELECTRONICS INC.

Inventor： Hyeonsik CHOI ,  Sungmoon CHO ,  Sangjun OH ,  Jaepil SEO

IPC: G06F18/21 ,  G01S3/80 ,  G06F18/214

CPC classification number: G06F18/217 ,  G01S3/8006 ,  G06F18/214

Abstract: An artificial intelligence (AI) apparatus including a memory and a processor configured to estimate a sound source localization based on at least one of image information, sound source information, and sensor information stored in the memory. The processor is configured to pre-process at least one of the image information, the sound source information, or the sensor information to generate test data, input the test data into a pre-trained AI model to estimate the sound source localization, calculate a sound source localization estimation evaluation score of the AI model for the test data, classify the test data into validation data based on the calculated sound source localization estimation evaluation score, change the AI model based on the classified validation data, and input the test data into the changed AI model to update the AI model.

公开(公告)号：US20210306746A1

公开(公告)日：2021-09-30

申请号：US17031565

申请日：2020-09-24

Applicant: LG ELECTRONICS INC.

Inventor： Sangjun OH ,  Senghyun HUANG ,  Youngman KIM ,  Kyuho LEE ,  Jaewoong JEONG

IPC: H04R3/04 ,  G10L25/51 ,  H04L29/06 ,  G06N3/08

Abstract: A sound quality improvement based on artificial intelligence is disclosed. A sound control method based on artificial intelligence according to an embodiment of the present disclosure provides a different call sound quality for each person based on a plurality of person information stored in an address book of a mobile terminal. The mobile terminal and 5G network of the present disclosure may be associated with an artificial intelligence module, a drone ((Unmanned Aerial Vehicle, UAV), a robot, an AR (Augmented Reality) device, a VR (Virtual Reality) device, a device associated with 5G services, etc.

公开(公告)号：US20190392811A1

公开(公告)日：2019-12-26

申请号：US16561707

申请日：2019-09-05

Applicant: LG ELECTRONICS INC.

Inventor： Kyuho LEE ,  Youngman KIM ,  Sangjun OH ,  Jaewoong JEONG ,  Seunghyun HWANG

IPC: G10K15/02 ,  G10L25/51 ,  G06F3/16 ,  H04R1/02 ,  H04R3/00 ,  H04R29/00 ,  G06N3/08

Abstract: A method for synthesizing an engine sound includes outputting a first synthesized engine sound, obtaining a change in a first surrounding noise environment, learning an artificial neural network to obtain first masking level information corresponding to the obtained change in the first surrounding noise environment, generating a second synthesized engine sound by correcting the first synthesized engine sound based on the obtained first masking level information, and outputting the generated second synthesized engine sound.

公开(公告)号：US20200023856A1

公开(公告)日：2020-01-23

申请号：US16588363

申请日：2019-09-30

Applicant: LG Electronics Inc.

Inventor： Youngman KIM ,  Sangjun OH ,  Jaewoong JEONG ,  Kyuho LEE ,  Seunghyun HWANG

IPC: B60W50/00 ,  G10L15/16 ,  G10L17/00 ,  B60R16/037

Abstract: Disclosed are a method for controlling a vehicle based on speaker recognition and an intelligent vehicle. A method for controlling a vehicle based on speaker recognition according to an embodiment of the present invention recognize a user boarding on a vehicle in accordance with utterance data of the user, and determines and then controls the interior state of the vehicle using an artificial neural network model trained in advance in accordance with a vehicle control pattern of the recognized user, thereby being able to a driving environment optimized in accordance with the user. A method for controlling a vehicle based on speaker recognition and an intelligent vehicle of the present invention may be associated with an artificial intelligence module, a drone ((Unmanned Aerial Vehicle, UAV), a robot, an AR (Augmented Reality) device, a VR (Virtual Reality) device, a device associated with 5G services, etc.

公开(公告)号：US20200013395A1

公开(公告)日：2020-01-09

申请号：US16577527

申请日：2019-09-20

Applicant: LG ELECTRONICS INC.

Inventor： Jaewoong JEONG ,  Youngman KIM ,  Sangjun OH ,  Kyuho LEE ,  Seunghyun HWANG

IPC: G10L15/20 ,  G10L21/0232 ,  G10L25/84 ,  G10L15/22 ,  G10L15/06

Abstract: Disclosed are an intelligent voice recognizing method, a voice recognizing device, and an intelligent computing device. According to an embodiment of the present invention, a method of intelligently recognizing a voice by a voice recognizing device obtains a microphone detection signal via at least one microphone, removes noise from the microphone detection signal based on a noise removal model, recognizes a voice from the noise-removed microphone detection signal, and updates the noise removal model based on the type of the noise detected from the microphone detection signal, thereby preventing deterioration of speech recognition performance. According to the present invention, one or more of the voice recognizing device, intelligent computing device, and server may be related to artificial intelligence (AI) modules, unmanned aerial vehicles (UAVs), robots, augmented reality (AR) devices, virtual reality (VR) devices, and 5G service-related devices.

公开(公告)号：US20200013394A1

公开(公告)日：2020-01-09

申请号：US16576539

申请日：2019-09-19

Applicant: LG ELECTRONICS INC.

Inventor： Jaewoong JEONG ,  Youngman KIM ,  Sangjun OH ,  Kyuho LEE ,  Seunghyun HWANG

IPC: G10L15/20 ,  G10L25/84 ,  G10L15/30

Abstract: Disclosed herein is a method for intelligently recognizing voice by a voice recognizing apparatus in various noise environments. The method includes acquiring a first noise level for an environment in which the voice recognizing apparatus is located, inputting the first noise level into a previously learned noise-sensitivity model to acquire a first optimum sensitivity, and recognizing a user's voice based on the first optimum sensitivity. The noise-sensitivity model is learned in a plurality of noise environments acquiring different noise levels, so that it is possible to accurately acquire an optimum sensitivity corresponding to a noise level depending on an operating state when an IoT device (voice recognizing apparatus) is in operation. At least one of the voice recognizing apparatus and an intelligent computing device of present disclosure can be associated with artificial intelligence modules, drones (unmanned aerial vehicles (UAVs)), robots, augmented reality (AR) devices, virtual reality (VR) devices, devices related to 5G service, etc.