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

IPC: G10L13/04 ,  G10L15/02 ,  G10L15/32 ,  G10L15/06

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.

公开(公告)号：US20220383581A1

公开(公告)日：2022-12-01

申请号：US17824455

申请日：2022-05-25

Applicant: Electronics and Telecommunications Research Institute

Inventor： Hyun Cheol KIM ,  HYUKMIN KWON ,  Jeongil SEO ,  Sangwoo AHN ,  Seung Jun YANG

IPC: G06T15/04 ,  G06T15/50 ,  G06T17/20

Abstract: Provided are a texture mapping method using a reference image, and a computing apparatus. In detail, a texture mapping method may provide color continuity using a reference image and a target image with respect to each triangular face without analyzing a spatial configuration of a three-dimensional mesh model, thereby reducing a sense of color difference with respect to a texture, and improving quality of the three-dimensional mesh model.

公开(公告)号：US20210248815A1

公开(公告)日：2021-08-12

申请号：US17171466

申请日：2021-02-09

Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE

Inventor： Hyun Cheol KIM ,  Hyuk Min KWON ,  Jeong Il SEO ,  Sang Woo AHN ,  Seung Jun YANG

IPC: G06T17/00 ,  G06F17/18

Abstract: Disclosed herein a method of removing a point cloud outlier and an apparatus implementing the method. The method includes: arranging a point cloud obtained from a laser scanner along at least a first direction; selecting, neighboring first-axis points, between which a separation degree satisfies an inspection start threshold condition, as a first leading-side representative point and a first trailing-side representative point; selecting a first leading-side outlier candidate and a first trailing-side outlier candidate based on a first leading-side separation degree and a first trailing-side separation degree; and determining the first leading-side outlier candidate and the first trailing-side outlier candidate as a first outlier point, when the number of the outlier candidates satisfies an allowable threshold condition.

公开(公告)号：US20180060682A1

公开(公告)日：2018-03-01

申请号：US15662616

申请日：2017-07-28

Applicant: Electronics and Telecommunications Research Institute

Inventor： Yong Ju CHO ,  Soon-heung JUNG ,  Hyun Cheol KIM ,  Jeongil SEO ,  Joo Myoung SEOK ,  Sangwoo AHN ,  Seung Jun YANG ,  Injae LEE ,  Hee Kyung LEE ,  Seong Yong LIM

IPC: G06K9/20 ,  H04N13/02 ,  H04N9/097 ,  G06T3/00

CPC classification number: G06K9/20 ,  G06K9/00771 ,  G06K2009/2045 ,  G06T3/0081 ,  G06T3/4038 ,  H04N5/23238 ,  H04N5/2622 ,  H04N9/097 ,  H04N13/225 ,  H04N13/239 ,  H04N2013/0088

Abstract: Provided is a parallax minimization stitching method and apparatus using control points in an overlapping region. A parallax minimization stitching method may include defining a plurality of control points in an overlapping region of a first image and a second image received from a plurality of cameras, performing a first geometric correction by applying a homography to the control points, defining a plurality of patches based on the control points, and performing a second geometric correction by mapping the patches.

公开(公告)号：US20140177967A1

公开(公告)日：2014-06-26

申请号：US14141171

申请日：2013-12-26

Applicant: Myongji University Industry and Academia Cooperation Foundation ,  Electronics and Telecommunications Research Institute

Inventor： Seung Jun YANG ,  Sang Kyun KIM ,  Yong Soo JOO

IPC: G06K9/00

CPC classification number: G06K9/00664

Abstract: An emotion information conversion apparatus and method is provided. The emotion information conversion apparatus includes a visual information extractor to extract visual information from an input image, an emotion information converter to analyze the extracted visual information and convert the visual information into emotion information, and a sensory effect information generator to generate sensory effect information transferable to a user, based on the converted emotion information.

Abstract translation: 提供了情感信息转换装置和方法。 情绪信息转换装置包括从输入图像提取视觉信息的视觉信息提取器，用于分析所提取的视觉信息并将视觉信息转换为情感信息的情绪信息转换器，以及感觉效果信息发生器，以生成可传播感觉效果信息 基于转换的情绪信息向用户发送。