-
11.发明申请公开(公告)号：US20130322666A1
公开(公告)日：2013-12-05
申请号：US13834936
申请日：2013-03-15
Inventor： Jae Hyoun YOO , Keun Woo CHOI , Jeong Il SEO , Kyeong Ok KANG
IPC: H04R5/04
CPC classification number: H04R5/04 , H04R3/12 , H04R2203/12
Abstract: A Method for processing an audio signal to use a beamforming technique in a three-dimensional (3D) space is disclosed. The method may include generating a beamforming signal on a horizontal plane related to a sound source in a three-dimensional (3D) space and modulating the beamforming signal to head for a listener in the 3D space from the sound source.
Abstract translation: 公开了一种在三维（3D）空间中处理音频信号以使用波束形成技术的方法。 该方法可以包括在与三维（3D）空间中的声源相关的水平平面上生成波束形成信号，并且将该波束形成信号调制为来自声源的3D空间中的收听者。
-
公开(公告)号：US20130170651A1
公开(公告)日：2013-07-04
申请号：US13733617
申请日：2013-01-03
Inventor： Yong Ju LEE , Jeong Il SEO , Keun Woo CHOI , Kyeong Ok KANG
IPC: H04R3/12
CPC classification number: H04R3/12 , H04S7/30 , H04S2400/11
Abstract: An apparatus and method for generating a multichannel audio signal showing a 3-dimensional (3D) effect by editing an existing multichannel audio signal. The apparatus may include an output location determiner to determine location to output an object audio signal using editing information of the object audio signal, and a multichannel object audio signal generator to generate a multichannel object audio signal by allocating the object audio signal to channels corresponding to the location to output the object audio signal.
Abstract translation: 一种用于通过编辑现有多声道音频信号来产生表示三维（3D）效果的多声道音频信号的装置和方法。 该装置可以包括输出位置确定器，用于使用对象音频信号的编辑信息来确定输出对象音频信号的位置;以及多声道对象音频信号发生器，通过将对象音频信号分配给与第 输出对象音频信号的位置。
-
公开(公告)号：US20240135595A1
公开(公告)日：2024-04-25
申请号：US18489359
申请日：2023-10-17
Inventor： Da Yun NAM , Hyun Cheol KIM , Jeong Il SEO , Seong Yong LIM , Chae Eun RHEE , Gwang Cheol RYU , Yong Wook SEO , Hyun Min JUNG
CPC classification number: G06T9/001 , G06T19/00 , G06T2210/32 , G06T2210/36
Abstract: The present invention relates to a method and apparatus for encoding a displacement video using image tiling. A method for encoding multi-dimensional data according to an embodiment of the present disclosure may comprise: converting the multi-dimensional data into one or more frames with two-dimensional characteristics; generating one or more frame groups by grouping the one or more frames with pre-configured number units; reconstructing frames belonging to each frame group into a tiled frame; and generating a bitstream by encoding the tiled frame. Here, the tiled frame may be constructed with one or more blocks, and each block may be constructed by rearranging pixels existing at the same location in the frames.
-
公开(公告)号：US20230222694A1
公开(公告)日：2023-07-13
申请号：US18096415
申请日：2023-01-12
Applicant: Electronics and Telecommunications Research Institute , IUCF-HYU (Industry-University Cooperation Foundation Hanyang University)
Inventor： Kwan Jung OH , Gwang Soon LEE , Jeong Il SEO , Hong Chang SHIN , Jun Young JEONG , Euee Seon JANG , Tian Yu Dong , Xin Li , Jai Young OH
CPC classification number: G06T9/00 , G06T7/194 , G06T7/60 , G06T2207/20132
Abstract: A method of processing an immersive video according to the present disclosure includes performing pruning for an input image, generating an atlas based on patches generated by the pruning and generating a cropped atlas by removing a background region of the atlas.
-
公开(公告)号：US20200372620A1
公开(公告)日：2020-11-26
申请号：US16882089
申请日：2020-05-22
Inventor： Yong Ju CHO , Soon Heung JUNG , Jeong Il SEO
Abstract: The present invention provides a method for image preprocessing, the method including: identifying a plurality of input images to process image registration; selecting at least one transformation method among histogram equalization and gamma transformation in consideration of hue and brightness values of the plurality of input images; processing the histogram equalization on the plurality of input images in response to the histogram equalization method being selected; and processing the gamma transformation on the plurality of input images, in response to the gamma transformation method being selected.
-
Patent Agency Ranking
公开(公告)号：US20200372350A1
公开(公告)日：2020-11-26
申请号：US16879885
申请日：2020-05-21
Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE , INFORMATION TECHNOLOGY UNIVERSITY (ITU)
Inventor： Yong Ju CHO , Jeong Il SEO , Rehan Hafiz , Mohsen Ali , Muhammad Faisal , Aman Irshad
Abstract: Disclosed herein is an image deep learning model training method. The method includes sampling a twin negative comprising a first negative sample and a second negative sample by selecting the first negative sample with a highest similarity out of an anchor sample and a positive sample constituting a matching pair in each class and by selecting the second negative sample with a highest similarity to the first negative sample, and training the samples to minimize a loss of a loss function in each class by utilizing the anchor sample, the positive sample, the first and second negative samples for each class. The first negative sample is selected in a different class from a class comprising the matching pair, and the second negative sample is selected in a different class from classes comprising the matching pair and the first negative sample.
-
公开(公告)号：US20190289413A1
公开(公告)日：2019-09-19
申请号：US16357180
申请日：2019-03-18
Inventor： Seung Kwon BEACK , Jeong Il SEO , Jong Mo SUNG , Tae Jin LEE , Dae Young JANG , Jin Woong KIM
IPC: H04S3/00 , G10L19/008 , G10L19/20
Abstract: Disclosed are a multi-channel audio signal processing method and a multi-channel audio signal processing apparatus. The multi-channel audio signal processing method may generate N channel output signals from N/2 channel downmix signals based on an N−N/2−N structure.
-
18.发明申请公开(公告)号：US20190019500A1
公开(公告)日：2019-01-17
申请号：US16035261
申请日：2018-07-13
Applicant: Electronics and Telecommunications Research Institute , YONSEI UNIVERSITY INDUSTRY FOUNDATION (YONSEI UIF)
Inventor： In Seon JANG , Hong Goo KANG , Hyeon Joo KANG , Young Sun Joo , Chung Hyun AHN , Jeong Il SEO , Seung Jun YANG , Ji Hoon CHOI
Abstract: Disclosed is a method and apparatus for training a speech signal. A speech signal training apparatus of the present disclosure may include a target speaker speech database storing a target speaker speech signal; a multi-speaker speech database storing a multi-speaker speech signal; a target speaker acoustic parameter extracting unit extracting an acoustic parameter of a training subject speech signal from the target speaker speech signal; a similar speaker acoustic parameter determining unit extracting at least one similar speaker speech signal from the multi-speaker speech signals, and determining an auxiliary speech feature of the similar speaker speech signal; and an acoustic parameter model training unit determining an acoustic parameter model by performing model training for a relation between the acoustic parameter and text by using the acoustic parameter and the auxiliary speech feature, and setting mapping information of the relation between the acoustic parameter model and the text.
-
19.发明申请公开(公告)号：US20180035230A1
公开(公告)日：2018-02-01
申请号：US15551734
申请日：2016-02-17
Inventor： Seung Kwon BEACK , Jeong Il SEO , Jong Mo SUNG , Tae Jin LEE , Dae Young JANG , Jin Soo CHOI
IPC: H04S1/00 , H04S5/00 , G10L19/008
CPC classification number: H04S1/007 , G10L19/008 , H04S3/008 , H04S3/02 , H04S5/00 , H04S2400/01 , H04S2400/03 , H04S2400/07 , H04S2420/03
Abstract: Provided are an encoding method of a multichannel signal, an encoding apparatus to perform the encoding method, a multichannel signal processing method, and a decoding apparatus to perform the decoding method. The decoding method may include identifying an N/2-channel downmix signal derived from an N-channel input signal; and generating an N-channel output signal from the identified N/2-channel downmix signal using a plurality of one-to-two (OTT) boxes. If a low frequency effect (LFE) channel is absent in the output signal, the number of OTT boxes may be equal to N/2 where N/2 denotes the number of channels of the downmix signal.
-
20.发明申请公开(公告)号：US20170278521A1
公开(公告)日：2017-09-28
申请号：US15620119
申请日：2017-06-12
Inventor： Seung Kwon BEACK , Tae Jin LEE , Jong Mo SUNG , Jeong Il SEO , Kyeong Ok KANG , Dae Young JANG , Jin Woong KIM
IPC: G10L19/008 , H04S3/00
CPC classification number: G10L19/008 , H04S3/008 , H04S2400/03
Abstract: An encoder and an encoding method for a multi-channel signal, and a decoder and a decoding method for a multi-channel signal are disclosed. A multi-channel signal may be efficiently processed by consecutive downmixing or upmixing.
-
-
-
-
-
-
-
-
-
Search Results
52
records
(took 0.027 seconds)
