公开(公告)号：US10923106B2

公开(公告)日：2021-02-16

申请号：US16256835

申请日：2019-01-24

Applicant: Korea Electronics Technology Institute

Inventor： Jong Yeol Yang ,  Young Han Lee ,  Choong Sang Cho ,  Hye Dong Jung

IPC: G10L13/00 ,  G10L13/10 ,  H04N21/233 ,  G06K9/00

Abstract: An audio synthesis method adapted to video characteristics is provided. The audio synthesis method according to an embodiment includes: extracting characteristics x from a video in a time-series way; extracting characteristics p of phonemes from a text; and generating an audio spectrum characteristic St used to generate an audio to be synthesized with a video at a time t, based on correlations between an audio spectrum characteristic St-1, which is used to generate an audio to be synthesized with a video at a time t−1, and the characteristics x. Accordingly, an audio can be synthesized according to video characteristics, and speech according to a video can be easily added.

公开(公告)号：US11482134B2

公开(公告)日：2022-10-25

申请号：US16536151

申请日：2019-08-08

Applicant: KOREA ELECTRONICS TECHNOLOGY INSTITUTE

Inventor： Hye Dong Jung ,  Sang Ki Ko ,  Han Mu Park ,  Chang Jo Kim

IPC: G09B21/00 ,  G06T11/00 ,  G10L15/22 ,  G10L15/24 ,  G10L25/63 ,  G10L25/90 ,  G06V40/20 ,  G06V40/16

Abstract: Disclosed is a method of providing a sign language video reflecting an appearance of a conversation partner. The method includes recognizing a speech language sentence from speech information, and recognizing an appearance image and a background image from video information. The method further comprises acquiring multiple pieces of word-joint information corresponding to the speech language sentence from joint information database, sequentially inputting the word-joint information to a deep learning neural network to generate sentence-joint information, generating a motion model on the basis of the sentence-joint information, and generating a sign language video in which the background image and the appearance image are synthesized with the motion model. The method provides a natural communication environment between a sign language user and a speech language user.

公开(公告)号：US10978049B2

公开(公告)日：2021-04-13

申请号：US16256563

申请日：2019-01-24

Applicant: Korea Electronics Technology Institute

Inventor： Young Han Lee ,  Jong Yeol Yang ,  Choong Sang Cho ,  Hye Dong Jung

IPC: G10L15/16 ,  G10L13/00 ,  G10L15/14 ,  G10L15/04 ,  G06N20/10 ,  G06N7/00 ,  G10L13/08 ,  G06F40/216

Abstract: An audio segmentation method based on an attention mechanism is provided. The audio segmentation method according to an embodiment obtains a mapping relationship between an “inputted text” and an “audio spectrum feature vector for generating an audio signal”, the audio spectrum feature vector being automatically synthesized by using the inputted text, and segments an inputted audio signal by using the mapping relationship. Accordingly, high quality can be guaranteed and the effort, time, and cost can be noticeably reduced through audio segmentation utilizing the attention mechanism.

公开(公告)号：US11741755B2

公开(公告)日：2023-08-29

申请号：US16942985

申请日：2020-07-30

Applicant: Korea Electronics Technology Institute

Inventor： Sang Ki Ko ,  Hye Dong Jung ,  Han Mu Park ,  Chang Jo Kim

IPC: G06V40/00 ,  G06V40/20 ,  G06F3/01 ,  G06N3/084 ,  G10L13/00 ,  G06N3/045 ,  G10L15/24 ,  G06V10/764 ,  G06V10/82 ,  G06V10/44

CPC classification number: G06V40/28 ,  G06F3/011 ,  G06F3/017 ,  G06N3/045 ,  G06N3/084 ,  G06V10/454 ,  G06V10/764 ,  G06V10/82 ,  G10L13/00 ,  G10L15/24

Abstract: A method and apparatus for recognizing a sign language or a gesture by using a three-dimensional (3D) Euclidean distance matrix (EDM) are disclosed. The method includes a two-dimensional (2D) EDM generation step for generating a 2D EDM including information about distances between feature points of a body recognized in image information by a 2D EDM generator, a 3D EDM generation step for receiving the 2D EDM and generating a 3D EDM by using a first deep learning neural network trained with training data in which input data is a 2D EDM and correct answer data is a 3D EDM by a 3D EDM generator, and a recognition step for recognizing a sign language or a gesture based on the 3D EDM.

公开(公告)号：US10230615B2

公开(公告)日：2019-03-12

申请号：US15331621

申请日：2016-10-21

Applicant: Korea Electronics Technology Institute

Inventor： Hye Dong Jung

IPC: H04L12/26 ,  H04L29/08

Abstract: A method for optimizing network performance according to an embodiment of the present invention includes initializing a size of test data for network performance measurement, performing a test on the network performance by transmitting the test data to each of a first communication protocol and a second communication protocol, repeatedly performing the test, when the size of the test data is increased and then the increased size of the test data is a preset size or smaller based on a comparison between the increased size of the test data and the preset size, and setting a threshold value having a data size being a reference of switching between the first communication protocol and the second communication protocol, based on data collected through the performing of the test, when the increased size of the test data is larger than the preset size.

公开(公告)号：US11386292B2

公开(公告)日：2022-07-12

申请号：US17016654

申请日：2020-09-10

Applicant: Korea Electronics Technology Institute

Inventor： Bo Eun Kim ,  Hye Dong Jung

IPC: G06K9/62 ,  G06F40/10

Abstract: A method and a system for automatically generating multiple captions of an image are provided. A method for training an auto image caption generation model according to an embodiment of the present disclosure includes: generating a caption attention map by using an image; converting the generated caption attention map into a latent variable by projecting the caption attention map onto a latent space; deriving a guide map by using the latent variable; and training to generate captions of an image by using the guide map and the image. Accordingly, a plurality of captions describing various characteristics of an image and including various expressions can be automatically generated.

公开(公告)号：US10726289B2

公开(公告)日：2020-07-28

申请号：US16043338

申请日：2018-07-24

Applicant: Korea Electronics Technology Institute

Inventor： Bo Eun Kim ,  Choong Sang Cho ,  Hye Dong Jung ,  Young Han Lee

IPC: G06K9/46 ,  G06T7/00 ,  G06N5/04 ,  G06N3/08 ,  G06F40/20 ,  G06F40/169 ,  G06N3/04 ,  G06N5/02

Abstract: A method and a system for automatic image caption generation are provided. The automatic image caption generation method according to an embodiment of the present disclosure includes: extracting a distinctive attribute from example captions of a learning image; training a first neural network for predicting a distinctive attribute from an image, by using a pair of the extracted distinctive attribute and the learning image; inferring a distinctive attribute by inputting the learning image to the trained first neural network; and training a second neural network for generating a caption of an image by using a pair of the inferred distinctive attribute and the learning image. Accordingly, a caption well indicating a feature of a given image is automatically generated, such that an image can be more exactly explained and a difference from other images can be clearly distinguished.

公开(公告)号：US09811501B2

公开(公告)日：2017-11-07

申请号：US14926850

申请日：2015-10-29

Applicant: Korea Electronics Technology Institute

Inventor： Bong Jae Kim ,  Hye Dong Jung

IPC: H04L29/08 ,  G06F15/167 ,  G06N7/00

CPC classification number: G06F15/167 ,  G06N7/005 ,  H04L67/1097

Abstract: A local processing apparatus and a data transceiving method thereof are provided. The local processing apparatus includes a communication module configured to transceive the data with the one or more distributed storage units, a memory configured to store a program for transceiving the data and the one or more key-value data pairs, and a processor configured to execute the program, the processor confirms whether a first key-value data exists in the memory by executing the program, and determines whether to prefetch one or more key-value data corresponding to the first key-value data based on the confirmation result.

公开(公告)号：US20170118107A1

公开(公告)日：2017-04-27

申请号：US15331621

申请日：2016-10-21

Applicant: Korea Electronics Technology Institute

Inventor： Hye Dong Jung

IPC: H04L12/26 ,  H04L29/08

CPC classification number: H04L43/50 ,  H04L43/16 ,  H04L67/10

Abstract: A method for optimizing network performance according to an embodiment of the present invention includes initializing a size of test data for network performance measurement, performing a test on the network performance by transmitting the test data to each of a first communication protocol and a second communication protocol, repeatedly performing the test, when the size of the test data is increased and then the increased size of the test data is a preset size or smaller based on a comparison between the increased size of the test data and the preset size, and setting a threshold value having a data size being a reference of switching between the first communication protocol and the second communication protocol, based on data collected through the performing of the test, when the increased size of the test data is larger than the preset size.