专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

WO2023085587A1 ARTIFICIAL INTELLIGENCE APPARATUS AND METHOD FOR DETECTING UNSEEN CLASS ITEMS THEREOF 审中-公开
公开(公告)号：WO2023085587A1
公开(公告)日：2023-05-19
申请号：PCT/KR2022/014027
申请日：2022-09-20
申请人： LG ELECTRONICS INC.
发明人： KIM, Hyoeun , LEE, Kamin , CHAE, Seungah , CHOI, Heeyeon , JUNG, Yeonjee , JEON, Hyejeong
IPC分类号： G06V10/764 , G06V20/40 , G06N3/08 , H04N19/136
摘要： The present disclosure relates to an artificial intelligence apparatus capable of classifying and detecting an item of an unseen class having high visual similarity to an item of a seen class that has been learned and known in advance, and a method for detecting an unseen class items thereof, and when the item image is input, generate encoded data by encoding the item image, generate decoded data by decoding the encoded data using a codebook of a plurality of codebooks in which encoded data for each item class is stored, corresponding to a pre-learned item class, and detect the unknown item by classifying the class of the item image based on the generated decoded data.

2. 发明公开

EP3772710A1 ARTIFICIAL INTELLIGENCE SERVER 审中-实审
公开(公告)号：EP3772710A1
公开(公告)日：2021-02-10
申请号：EP20171744.4
申请日：2020-04-28
申请人： LG Electronics Inc.
发明人： HAN, Jongwoo , KIM, Jaehong , KIM, Hyoeun , LEE, Taeho , JEON, Hyejeong , JEONG, Hangil , CHOI, Heeyeon
IPC分类号： G06N20/00
摘要： An artificial intelligence server is disclosed. The artificial intelligence server includes an input unit to which input data is inputted, and a processor, when a first output value outputted by an artificial intelligence model with respect to first input data is correct and a second output value outputted by the artificial intelligence model with respect to second input data is incorrect, configured to use the first input data and the second input data to obtain a first domain causing an incorrect answer, and train the artificial intelligence model to be domain-adapted for the first domain.

3. 发明公开

EP3457398A1 ELECTRONIC DEVICE AND CONTROL METHOD THEREFOR 有权
公开(公告)号：EP3457398A1
公开(公告)日：2019-03-20
申请号：EP16901780.3
申请日：2016-10-10
申请人： LG Electronics Inc.
发明人： LEE, Byounggi , JEON, Hyejeong
IPC分类号： G10L15/20 , G10L15/22 , H04R19/04 , G10L15/06
摘要： Disclosed are an electronic device capable of performing a function or an operation according to a voice command inputted through a microphone, and a control method therefore, the device comprising: a voice acquisition microphone for receiving a voice signal including noise having a first strength; a noise acquisition microphone for receiving a voice signal including noise having a second strength, which is greater than the first strength; and a control unit for estimating the noise having the second strength from the voice signal received from the noise acquisition microphone, removing the noise having the first strength, from the voice signal received from the voice acquisition microphone, on the basis of the estimated noise, and performing an operation corresponding to the voice signal from which the noise having the first strength is removed.

4. 发明授权

EP2610866B1 METHOD AND DEVICE FOR PROCESSING AUDIO SIGNALS 有权
标题翻译：方法和设备用于处理音频信号
公开(公告)号：EP2610866B1
公开(公告)日：2015-04-22
申请号：EP11820168.0
申请日：2011-08-23
申请人： LG Electronics Inc.
发明人： LEE, Changheon , JEONG, Gyuhyeok , KIM, Lagyoung , JEON, Hyejeong , LEE, Byungsuk , KANG, Ingyu
IPC分类号： G10L19/038 , G10L19/02 , G10L19/04 , G10L19/00
CPC分类号： G10L19/008 , G10L19/02 , G10L19/038 , G10L19/04 , G10L2019/0005
摘要： The present invention provides a method for processing audio signals, and the method comprises the steps of: receiving input audio signals corresponding to a plurality of spectral coefficients; obtaining location information that indicates a location of a particular spectral coefficient among said spectral coefficients, on the basis of energy of said input signals: generating a shape vector by using said location information and said spectral coefficients; determining a codebook index by searching for a codebook corresponding to said shape vector; and transmitting said codebook index and said location information, wherein said shape vector is generated by using a part which is selected from said spectral coefficients, and said selected part is selected on the basis of said location information.

5. 发明公开

EP2772911A1 METHOD AND DEVICE FOR QUANTIZING VOICE SIGNALS IN A BAND-SELECTIVE MANNER 失效
标题翻译：方法和装置QUANTIZE语音信号在乐队选择的方式
公开(公告)号：EP2772911A1
公开(公告)日：2014-09-03
申请号：EP12844438.7
申请日：2012-05-04
申请人： LG Electronics Inc. , Chungbuk National University Industry Academic Cooperation Foundation
发明人： JEONG, Gyuhyeok , LEE, Younghan , HONG, Kibong , JEON, Hyejeong , LEE, Insung , KANG, Ingyu , KIM, Lagyoung
IPC分类号： G10L19/00
CPC分类号： G10L19/265 , G10L19/0204 , G10L19/032
摘要： The present invention relates to a method and device for quantizing voice signals in a band-selective manner. A Voice decoding method may include inversely quantizing voice parameter information produced from a selectively quantized voice band and performing inverse transform on the basis of the inversely quantized voice parameter information. Thus, according to the present invention, coding/decoding efficiency in voice coding/decoding may be increased by selectively coding/decoding important information.
摘要翻译：本发明涉及一种用于在一个带选择性的方式量化语音信号的方法和设备。的语音译码方法可以包括逆量化来自量化选择性语音磁带产生语音参数信息，并执行逆的逆量化语音的基础上变换参数的信息。因此，gemäß到本发明中，编码/解码的声音编码/解码效率可以通过选择性地编码/解码的重要信息被增加。

6. 发明公开

EP2763137A2 VOICE SIGNAL ENCODING METHOD, VOICE SIGNAL DECODING METHOD, AND APPARATUS USING SAME 有权
标题翻译：语音信号编码方法，语音信号解码方法和使用该方法的装置
公开(公告)号：EP2763137A2
公开(公告)日：2014-08-06
申请号：EP12836122.7
申请日：2012-09-28
申请人： LG Electronics Inc.
发明人： LEE, Younghan , JEONG, Gyuhyeok , KANG, Ingyu , JEON, Hyejeong , KIM, Lagyoung
IPC分类号： G10L19/00
CPC分类号： G10L19/02 , G10L19/0212 , G10L19/032 , G10L19/24
摘要： 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.
摘要翻译：用于处理语音信号的方法和设备本发明涉及一种用于处理语音信号的方法和设备，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生成形成输入语音信号的正弦波分量的变换系数; 从所产生的变换系数确定要被编码的变换系数; 并且发送指示所确定的变换系数的指示信息，其中所述指示信息可以包括所述变换系数的位置信息，幅度信息和符号信息。

7. 发明授权

EP2637073B1 Robot cleaner and method for controlling the same 有权转让
公开(公告)号：EP2637073B1
公开(公告)日：2019-12-18
申请号：EP13158036.7
申请日：2013-03-06
申请人： LG Electronics Inc.
发明人： LEE, Heungkyu , JEON, Hyejeong , LEE, Byounggi
IPC分类号： G05D1/02 , G08B13/19 , G10L25/51

8. 发明公开

EP2897127A1 FRAME LOSS RECOVERING METHOD, AND AUDIO DECODING METHOD AND DEVICE USING SAME 失效
标题翻译： VERFAHREN ZUR RAHMENVERLUSTWIEDERHERSTELLUNG UND TONDECODIERVERFAHREN SOWIE VORRICHTUNG DAMIT
公开(公告)号：EP2897127A1
公开(公告)日：2015-07-22
申请号：EP13837778.3
申请日：2013-09-11
申请人： LG Electronics Inc.
发明人： JEONG, Gyuhyeok , JEON, Hyejeong , KANG, Ingyu
IPC分类号： G10L19/005
CPC分类号： G10L19/005 , G10L19/0204 , G10L19/12
摘要： 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.
摘要翻译：本发明涉及一种帧丢失恢复方法，音频解码方法以及使用该方法的装置。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到当前帧的前一帧来恢复当前帧的变换系数。

9. 发明公开

EP2772909A1 METHOD FOR ENCODING VOICE SIGNAL, METHOD FOR DECODING VOICE SIGNAL, AND APPARATUS USING SAME 有权
标题翻译：法语音信号进行编码的，解码语音信号及装置的方法
公开(公告)号：EP2772909A1
公开(公告)日：2014-09-03
申请号：EP12843449.5
申请日：2012-10-29
申请人： LG Electronics Inc.
发明人： LEE, Younghan , JEONG, Gyuhyeok , KANG, Ingyu , JEON, Hyejeong , KIM, Lagyoung
IPC分类号： G10L19/00
CPC分类号： G10L21/02 , G10L19/002 , G10L19/005 , G10L19/025 , G10L19/24
摘要： The present invention relates to a method for encoding a voice signal, a method for decoding a voice signal, and an apparatus using the same. The method for encoding the voice signal according to the present invention, includes the steps of: determining an eco-zone in a present frame; allocating bits for the present frame on the basis of the location of the eco-zone; and encoding the present frame using the allocated bits, wherein the step of allocating the bits allocates more bits in the section in which the eco-zone is located than in the section in which the eco-zone is not located.
摘要翻译：本发明涉及一种用于编码语音信号，对于语音信号进行解码的方法，以及设备使用相同的。用于语音信号编码gemäß在本发明的方法中，包括以下步骤：在当前帧的生态区域的确定性开采; 分配用于生态区的位置的基础上，本帧比特; 和编码使用所分配的比特的当前帧，worin分配比特的步骤分配在其中生态区位于比其中生态区不位于区段的区段更多的比特。

10. 发明公开

EP2610866A2 METHOD AND DEVICE FOR PROCESSING AUDIO SIGNALS 有权
标题翻译： VERFAHREN UND VORRICHTUNG ZUR VERARBEITUNG VON AUDIOSIGNALEN
公开(公告)号：EP2610866A2
公开(公告)日：2013-07-03
申请号：EP11820168.0
申请日：2011-08-23
申请人： LG Electronics Inc.
发明人： LEE, Changheon , JEONG, Gyuhyeok , KIM, Lagyoung , JEON, Hyejeong , LEE, Byungsuk , KANG, Ingyu
IPC分类号： G10L19/00 , G11B20/10
CPC分类号： G10L19/008 , G10L19/02 , G10L19/038 , G10L19/04 , G10L2019/0005
摘要： The present invention provides a method for processing audio signals, and the method comprises the steps of: receiving input audio signals corresponding to a plurality of spectral coefficients; obtaining location information that indicates a location of a particular spectral coefficient among said spectral coefficients, on the basis of energy of said input signals: generating a shape vector by using said location information and said spectral coefficients; determining a codebook index by searching for a codebook corresponding to said shape vector; and transmitting said codebook index and said location information, wherein said shape vector is generated by using a part which is selected from said spectral coefficients, and said selected part is selected on the basis of said location information.
摘要翻译：本发明提供一种处理音频信号的方法，该方法包括以下步骤：接收对应于多个频谱系数的输入音频信号; 基于所述输入信号的能量获得指示所述频谱系数中的特定频谱系数的位置的位置信息：通过使用所述位置信息和所述频谱系数产生形状矢量; 通过搜索与所述形状矢量对应的码本来确定码本索引; 以及发送所述码本索引和所述位置信息，其中通过使用从所述频谱系数中选择的部分来生成所述形状向量，并且所述选择的部分是基于所述位置信息来选择的。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式