公开(公告)号：US11385861B2

公开(公告)日：2022-07-12

申请号：US16663820

申请日：2019-10-25

Applicant: LG ELECTRONICS INC.

Inventor： Gyuhyeok Jeong

IPC: G06F3/16 ,  G06N20/00 ,  H04W4/70 ,  H04L12/28 ,  G06F1/3234 ,  G10L15/08 ,  G10L15/22 ,  H04W4/33 ,  G06N3/02

Abstract: The present specification relates to a smart controlling device capable of utilizing machine learning for voice recognition and a method of controlling therefor. The smart controlling device according to the present invention includes a receiver configured to receive an input including a command trigger, and a controller configured to detect one or more external display devices, select a display device of the detected one or more external display devices, cause a power status of the selected display device to be changed to a first state, and cause a response data corresponding to a first command data received after the command trigger to be output on a display of the selected display device.

公开(公告)号：US09472199B2

公开(公告)日：2016-10-18

申请号：US14347767

申请日：2012-09-28

Applicant: LG Electronics Inc.

Inventor： Younghan Lee ,  Gyuhyeok Jeong ,  Ingyu Kang ,  Hyejeong Jeon ,  Lagyoung Kim

IPC: G10L19/00 ,  G10L19/02 ,  G10L19/032 ,  G10L19/24

CPC classification number: G10L19/02 ,  G10L19/0212 ,  G10L19/032 ,  G10L19/24

Abstract: The present invention relates to a method and apparatus for processing a voice signal, and the voice signal encoding method according to the present invention comprises the steps of: generating transform coefficients of sine wave components forming an input voice signal by transforming the sine wave components; determining transform coefficients to be encoded from the generated transform coefficients; and transmitting indication information indicating the determined transform coefficients, wherein the indication information may include position information, magnitude information, and sign information of the transform coefficients.

Abstract translation: 本发明涉及一种用于处理语音信号的方法和装置，并且根据本发明的语音信号编码方法包括以下步骤：通过变换正弦波分量来产生形成输入语音信号的正弦波分量的变换系数; 从所生成的变换系数确定要编码的变换系数; 以及发送指示所确定的变换系数的指示信息，其中指示信息可以包括变换系数的位置信息，幅度信息和符号信息。

公开(公告)号：US20140236581A1

公开(公告)日：2014-08-21

申请号：US14347767

申请日：2012-09-28

Applicant: LG Electronics Inc.

Inventor： Younghan Lee ,  Gyuhyeok Jeong ,  Ingyu Kang ,  Hyejeong Jeon ,  Lagyoung Kim

IPC: G10L19/02

CPC classification number: G10L19/02 ,  G10L19/0212 ,  G10L19/032 ,  G10L19/24

Abstract: The present invention relates to a method and apparatus for processing a voice signal, and the voice signal encoding method according to the present invention comprises the steps of: generating transform coefficients of sine wave components forming an input voice signal by transforming the sine wave components; determining transform coefficients to be encoded from the generated transform coefficients; and transmitting indication information indicating the determined transform coefficients, wherein the indication information may include position information, magnitude information, and sign information of the transform coefficients.

Abstract translation: 本发明涉及一种用于处理语音信号的方法和装置，并且根据本发明的语音信号编码方法包括以下步骤：通过变换正弦波分量来产生形成输入语音信号的正弦波分量的变换系数; 从所生成的变换系数确定要编码的变换系数; 以及发送指示所确定的变换系数的指示信息，其中指示信息可以包括变换系数的位置信息，幅度信息和符号信息。

公开(公告)号：US11027962B2

公开(公告)日：2021-06-08

申请号：US16603333

申请日：2017-12-01

Applicant: LG ELECTRONICS INC.

Inventor： Gyuhyeok Jeong

IPC: G10L21/00 ,  G10L25/00 ,  B67D1/08 ,  G10L15/22 ,  G06N3/08

Abstract: The present invention relates to a beverage supply apparatus comprising a sensing unit, a microphone, an artificial intelligence unit and a control unit. The control unit: activates the microphone when an object is detected; recognizes first sound data of a user when the first sound data is sensed via the activated microphone; acquires information associated with the user on the basis of the first sound data; stores the acquired information associated with the user; and determines a menu corresponding to the object on the basis of the information associated with the user and the first sound data.

公开(公告)号：US20150255074A1

公开(公告)日：2015-09-10

申请号：US14427778

申请日：2013-09-11

Applicant: LG ELECTRONICS INC.

Inventor： Gyuhyeok Jeong ,  Hyejeong Jeon ,  Ingyu Kang

IPC: G10L19/005 ,  G10L19/12

CPC classification number: G10L19/005 ,  G10L19/0204 ,  G10L19/12

Abstract: The present invention relates to a frame loss recovering method, an audio decoding method, and an apparatus using the method. A method of recovering a frame loss of an audio signal according to the present invention includes: grouping transform coefficients of at least one frame into a predetermined number of bands among previous frames of a current frame; deriving an attenuation constant according to a tonality of the bands; and recovering transform coefficients of the current frame by applying the attenuation constant to the previous frame of the current frame.

Abstract translation: 本发明涉及一种帧丢失恢复方法，音频解码方法和使用该方法的装置。 根据本发明的恢复音频信号的帧丢失的方法包括：将当前帧的先前帧中的至少一帧的变换系数分组为预定数量的频带; 根据频带的音调导出衰减常数; 以及通过将衰减常数应用于当前帧的前一帧来恢复当前帧的变换系数。

公开(公告)号：US11372619B2

公开(公告)日：2022-06-28

申请号：US16663803

申请日：2019-10-25

Applicant: LG ELECTRONICS INC.

Inventor： Gyuhyeok Jeong

IPC: G06F3/16 ,  G06N20/00 ,  H04W4/70 ,  H04L12/28 ,  G06F1/3234 ,  G10L15/08 ,  G10L15/22 ,  H04W4/33 ,  G06N3/02

Abstract: The present specification relates to a smart controlling device capable of utilizing machine learning for voice recognition and a method of controlling therefor. The smart controlling device according to the present invention includes a receiver configured to receive an input including a command trigger, and a controller configured to detect one or more external display devices, select a display device of the detected one or more external display devices, cause a power status of the selected display device to be changed to a first state, and cause a response data corresponding to a first command data received after the command trigger to be output on a display of the selected display device.

公开(公告)号：US10580400B2

公开(公告)日：2020-03-03

申请号：US15891625

申请日：2018-02-08

Applicant: LG ELECTRONICS INC.

Inventor： Gyuhyeok Jeong

IPC: G10L15/00 ,  G10L15/187 ,  G10L15/22 ,  G10L15/30 ,  G10L15/02

Abstract: This specification relates to a method for controlling an artificial intelligence system which performs a multilingual processing based on artificial intelligence technology. The method for controlling an artificial intelligence system which performs a multilingual processing includes: receiving voice information through a microphone; determining a language of the voice information, based on a preset reference; selecting a specific voice recognition server from a plurality of voice recognition servers which process different languages, based on a result of the determination; and transmitting the voice information to the selected specific voice recognition server.

公开(公告)号：US10191595B2

公开(公告)日：2019-01-29

申请号：US15476821

申请日：2017-03-31

Applicant: LG ELECTRONICS INC.

Inventor： Gyuhyeok Jeong ,  Taegil Cho

IPC: G06F3/043 ,  G06F3/041 ,  G06F3/16 ,  G10L15/22

Abstract: An electronic device including a plurality of the microphones and operating method thereof are disclosed. The present invention includes obtaining an audio according to a touch input of touching at least one of a plurality of the microphones, determining at least one selected from the group consisting of a location, a touch pattern, a touch strength, a touch duration time and a touch periodicity of the touch input based on the obtained audio, and performing an operation corresponding to the touch input based on a result of the determination.

公开(公告)号：US09633662B2

公开(公告)日：2017-04-25

申请号：US14427778

申请日：2013-09-11

Applicant: LG ELECTRONICS INC.

Inventor： Gyuhyeok Jeong ,  Hyejeong Jeon ,  Ingyu Kang

IPC: G10L19/005 ,  G10L19/12 ,  G10L19/02

CPC classification number: G10L19/005 ,  G10L19/0204 ,  G10L19/12

Abstract: The present invention relates to a frame loss recovering method, an audio decoding method, and an apparatus using the method. A method of recovering a frame loss of an audio signal according to the present invention includes: grouping transform coefficients of at least one frame into a predetermined number of bands among previous frames of a current frame; deriving an attenuation constant according to a tonality of the bands; and recovering transform coefficients of the current frame by applying the attenuation constant to the previous frame of the current frame.

公开(公告)号：US20140310008A1

公开(公告)日：2014-10-16

申请号：US14353044

申请日：2012-10-22

Applicant: LG Electronics Inc

Inventor： Ingyu Kang ,  Younghan Lee ,  Gyuhyeok Jeong ,  Hyejeong Jeon ,  Lagyoung Kim

IPC: G10L19/26

CPC classification number: G10L19/265 ,  G10L19/00 ,  G10L19/167 ,  G10L21/043 ,  H04J3/0632

Abstract: The present invention relates to a method of managing a jitter buffer and a jitter buffer using same. The method of managing a jitter buffer includes the steps of: receiving audio information frames; and adjusting a jitter buffer on the basis of the received audio information frames, wherein the adjusting step of the jitter buffer includes compensation of an audio signal, and the compensation of the audio signal can be performed for each sub frame of the audio information frames.

Abstract translation: 本发明涉及一种管理抖动缓冲器和使用其的抖动缓冲器的方法。 管理抖动缓冲器的方法包括以下步骤：接收音频信息帧; 以及基于接收到的音频信息帧调整抖动缓冲器，其中抖动缓冲器的调整步骤包括对音频信号的补偿，并且可以对音频信息帧的每个子帧执行音频信号的补偿。