-
公开(公告)号：US10963989B2
公开(公告)日：2021-03-30
申请号：US16155660
申请日：2018-10-09
Inventor： Soon Heung Jung , Yong Ju Cho , Jeong Il Seo
Abstract: Disclosed is an apparatus and method of generating a stitched image. A method of generating a stitched image according to the present disclosure includes: obtaining a plurality of input images; determining whether or not a parallax problem occurs between overlapping areas of the obtained input images; updating a predetermined look-up table according to the determination; and generating a stitched image by applying the updated look-up table to the input images.
-
公开(公告)号：US10701503B2
公开(公告)日：2020-06-30
申请号：US16126466
申请日：2018-09-10
Inventor： Yong Ju Lee , Jeong Il Seo , Seung Kwon Beack , Kyeong Ok Kang , Jin Woong Kim , Jae Hyoun Yoo
IPC: H04S3/00 , G10L19/008
Abstract: Disclosed is an apparatus and method for processing a multichannel audio signal. A multichannel audio signal processing method may include: generating an N-channel audio signal of N channels by down-mixing an M-channel audio signal of M channels; and generating a stereo audio signal by performing binaural rendering of the N-channel audio signal.
-
公开(公告)号：US10645514B2
公开(公告)日：2020-05-05
申请号：US16126466
申请日：2018-09-10
Inventor： Yong Ju Lee , Jeong Il Seo , Seung Kwon Beack , Kyeong Ok Kang , Jin Woong Kim , Jae Hyoun Yoo
IPC: H04S3/00 , G10L19/008
Abstract: Disclosed is an apparatus and method for processing a multichannel audio signal. A multichannel audio signal processing method may include: generating an N-channel audio signal of N channels by down-mixing an M-channel audio signal of M channels; and generating a stereo audio signal by performing binaural rendering of the N-channel audio signal.
-
公开(公告)号：US20180102131A1
公开(公告)日：2018-04-12
申请号：US15838031
申请日：2017-12-11
Inventor： Yong Ju Lee , Jeong Il Seo , Jae Hyoun Yoo , Seung Kwon Beack , Jong Mo Sung , Tae Jin Lee , Kyeong Ok Kang , Jin Woong Kim , Tae Jin Park , Dae Young Jang , Keun Woo Choi
IPC: G10L19/008 , H04S7/00
CPC classification number: H04S7/00 , G10L19/008 , H04S7/30 , H04S2400/01 , H04S2400/03
Abstract: Disclosed is a binaural rendering method and apparatus for decoding a multichannel audio signal. The binaural rendering method may include: extracting an early reflection component and a late reverberation component from a binaural filter; generating a stereo audio signal by performing binaural rendering of a multichannel audio signal base on the early reflection component; and applying the late reverberation component to the generated stereo audio signal.
-
公开(公告)号：US09312971B2
公开(公告)日：2016-04-12
申请号：US13729303
申请日：2012-12-28
Inventor： Jae Hyoun Yoo , Jeong Il Seo , Tae Jin Lee , Keun Woo Choi , Kyeong Ok Kang
IPC: H04R5/00 , H04H20/88 , G10L19/008 , G10L19/20 , G10L19/00
CPC classification number: H04H20/88 , G10L19/00 , G10L19/008 , G10L19/20 , H04R5/00 , H04S2400/00 , H04S2400/01 , H04S2420/13
Abstract: An apparatus and method for transmitting a plurality of audio objects using a multichannel encoder and a multichannel decoder are provided. The audio object encoder includes a multichannel encoder determination unit to determine a multichannel encoder to be used for encoding of a plurality of audio objects according to the number of the audio objects, an encoding unit to generate an encoded signal by encoding the plurality of audio objects using the determined multichannel encoder, and a multichannel audio object signal generation unit to generating a multichannel audio object signal, by multiplexing sound image localization information of the plurality of audio objects along with the encoded signal.
Abstract translation: 提供了一种使用多声道编码器和多声道解码器发送多个音频对象的装置和方法。 音频对象编码器包括多声道编码器确定单元，用于根据音频对象的数量确定要用于多个音频对象的编码的多声道编码器;编码单元，用于通过对多个音频对象进行编码来生成编码信号 使用所确定的多声道编码器和多声道音频对象信号生成单元，通过将多个音频对象的声音图像定位信息与编码信号一起多路复用来生成多声道音频对象信号。
-
Patent Agency Ranking
公开(公告)号：US12231864B2
公开(公告)日：2025-02-18
申请号：US18526897
申请日：2023-12-01
Inventor： Yong Ju Lee , Jeong Il Seo , Seung Kwon Beack , Kyeong Ok Kang , Jin Woong Kim , Jae Hyoun Yoo
IPC: H04S3/00 , G10L19/008 , G10L21/0316
Abstract: Disclosed is an apparatus and method for processing a multichannel audio signal. A multichannel audio signal processing method may include: generating an N-channel audio signal of N channels by down-mixing an M-channel audio signal of M channels; and generating a stereo audio signal by performing binaural rendering of the N-channel audio signal.
-
公开(公告)号：US11720790B2
公开(公告)日：2023-08-08
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
IPC: G06N3/08 , G06F18/22 , G06F18/23 , G06V10/82 , G06F17/16 , G06V10/764 , G06V10/77 , G06V10/774
CPC classification number: G06N3/08 , G06F17/16 , G06F18/22 , G06F18/23 , G06V10/764 , G06V10/774 , G06V10/7715 , G06V10/82
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：US11682402B2
公开(公告)日：2023-06-20
申请号：US17201943
申请日：2021-03-15
Inventor： Yong Ju Lee , Jeong Il Seo , Jae Hyoun Yoo , Seung Kwon Beack , Jong Mo Sung , Tae Jin Lee , Kyeong Ok Kang , Jin Woong Kim , Tae Jin Park , Dae Young Jang , Keun Woo Choi
IPC: G10L19/008 , H04S7/00
CPC classification number: G10L19/008 , H04S7/00 , H04S7/30 , H04S2400/01 , H04S2400/03
Abstract: Disclosed is a binaural rendering method and apparatus for decoding a multichannel audio signal. The binaural rendering method may include: extracting an early reflection component and a late reverberation component from a binaural filter; generating a stereo audio signal by performing binaural rendering of a multichannel audio signal base on the early reflection component; and applying the late reverberation component to the generated stereo audio signal.
-
公开(公告)号：US11405738B2
公开(公告)日：2022-08-02
申请号：US16703226
申请日：2019-12-04
Inventor： Yong Ju Lee , Jeong Il Seo , Seung Kwon Beack , Kyeong Ok Kang , Jin Woong Kim , Jae Hyoun Yoo
IPC: H04S3/00 , G10L19/008
Abstract: Disclosed is an apparatus and method for processing a multichannel audio signal. A multichannel audio signal processing method may include: generating an N-channel audio signal of N channels by down-mixing an M-channel audio signal of M channels; and generating a stereo audio signal by performing binaural rendering of the N-channel audio signal.
-
20.发明授权公开(公告)号：US11310615B2
公开(公告)日：2022-04-19
申请号：US16747372
申请日：2020-01-20
Inventor： Seung Kwon Beack , Tae Jin Lee , Jong Mo Sung , Kyeong Ok Kang , Jeong Il Seo , Dae Young Jang , Yong Ju Lee , Jin Woong Kim
IPC: H04S3/00 , G10L19/008
Abstract: An audio encoding apparatus and method that encodes hybrid contents including an object sound, a background sound, and metadata, and an audio decoding apparatus and method that decodes the encoded hybrid contents are provided. The audio encoding apparatus may include a mixing unit to generate an intermediate channel signal by mixing a background sound and an object sound, a matrix information encoding unit to encode matrix information used for the mixing, an audio encoding unit to encode the intermediate channel signal, and a metadata encoding unit to encode metadata including control information of the object sound.
-
-
-
-
-
-
-
-
-
Search Results
44
records
(took 0.019 seconds)
