公开(公告)号：US20210409687A1

公开(公告)日：2021-12-30

申请号：US17474514

申请日：2021-09-14

Applicant: Electronics and Telecommunications Research Institute

Inventor： Sung Chang LIM ,  Jong Ho KIM ,  Hae Chul CHOI ,  Hui Yong KIM ,  Ha Hyun LEE ,  Jin Ho LEE ,  Se Yoon JEONG ,  Suk Hee CHO ,  Jin Soo CHOI ,  Jin Woo HONG ,  Jin Woong KIM

IPC: H04N19/105 ,  H04N19/503 ,  H04N19/176 ,  H04N19/46 ,  H04N19/593 ,  H04N19/11 ,  H04N19/157

Abstract: Provided are an image encoding method and device. When carrying out image encoding for a block within a slice, at least one block in a restored block of the slice is set as a reference block. When this is done, the encoding parameters of the reference block are distinguished, and the block to be encoded is encoded adaptively based on the encoding parameters.

公开(公告)号：US20210390967A1

公开(公告)日：2021-12-16

申请号：US17242828

申请日：2021-04-28

Applicant: Electronics and Telecommunications Research Institute

Inventor： Seung Kwon Beack ,  Jongmo SUNG ,  Mi Suk LEE ,  Tae Jin LEE ,  Woo-taek LIM ,  Inseon JANG ,  Jin Soo CHOI

IPC: G10L19/032 ,  G10L19/08

Abstract: Disclosed is a method of encoding and decoding an audio signal using linear predictive coding (LPC) and an encoder and a decoder that perform the method. The method of encoding an audio signal to be performed by the encoder includes identifying a time-domain audio signal block-wise, quantizing a linear prediction coefficient obtained from a block of the audio signal through the LPC, generating an envelope based on the quantized linear prediction coefficient, extracting a residual signal based on the envelope and a result of converting the block into a frequency domain, grouping the residual signal by each sub-band and determining a scale factor for quantizing the grouped residual signal, quantizing the residual signal using the scale factor, and converting the quantized residual signal and the quantized linear prediction coefficient into a bitstream and transmitting the bitstream to a decoder.

公开(公告)号：US20210350796A1

公开(公告)日：2021-11-11

申请号：US17308800

申请日：2021-05-05

Applicant: Electronics and Telecommunications Research Institute ,  The Trustees of Indiana University

Inventor： Minje KIM ,  Mi Suk LEE ,  Seung Kwon BEACK ,  Jongmo SUNG ,  Tae Jin LEE ,  Jin Soo CHOI ,  Kai ZHEN

IPC: G10L15/16 ,  G06N3/04 ,  G06F17/15

Abstract: Disclosed is a speech processing apparatus and method using a densely connected hybrid neural network. The speech processing method includes inputting a time domain sample of N*1 dimension for an input speech into a densely connected hybrid network; passing the time domain sample through a plurality of dense blocks in a densely connected hybrid network; reshaping the time domain samples into M subframes by passing the time domain samples through the plurality of dense blocks, inputting the M subframes into gated recurrent unit (GRU) components of N/M-dimension; outputting clean speech from which noise is removed from the input speech by passing the M subframes through GRU components.

公开(公告)号：US20210227256A1

公开(公告)日：2021-07-22

申请号：US17221229

申请日：2021-04-02

Applicant: Electronics and Telecommunications Research Institute

Inventor： Jin Ho LEE ,  Hui Yong KIM ,  Sung Chang LIM ,  Jin Soo CHOI ,  Jin Woong KIM

IPC: H04N19/593 ,  H04N19/82 ,  H04N19/159 ,  H04N19/122 ,  H04N19/136 ,  H04N19/157 ,  H04N19/117 ,  H04N19/137 ,  H04N19/44 ,  H04N19/80 ,  H04N19/105 ,  H04N19/11 ,  H04N19/182

Abstract: According to the present invention, an image encoding/decoding method comprises the steps of: performing an intra prediction on a current block so as to generate a prediction block; performing filtering on a filtering target pixel in the prediction block on the basis of the intra prediction mode of the current block so as to generate a final prediction block; and generating a reconstructed block on the basis of a reconstructed differential block corresponding to the current block and on the final prediction block. According to the present invention, image encoding/decoding efficiency can be improved.

公开(公告)号：US20210174815A1

公开(公告)日：2021-06-10

申请号：US17112480

申请日：2020-12-04

Applicant: Electronics and Telecommunications Research Institute

Inventor： Seung Kwon BEACK ,  Jooyoung LEE ,  Jongmo SUNG ,  Mi Suk LEE ,  Tae Jin LEE ,  Woo-taek LIM ,  Seunghyun CHO ,  Jin Soo CHOI

IPC: G10L19/038 ,  G10L25/30 ,  G10L19/028 ,  G10L19/24 ,  G06N3/02

Abstract: Disclosed are a quantizing method for a latent vector and a computing device for performing the quantization method. A quantizing method of a latent vector includes performing information shaping on the latent vector resulting from reduction in a dimension of an input signal using a target neural network; clamping a residual signal of the latent vector derived based on the information shaping; performing resealing on the clamped residual signal; and performing quantization on the resealed residual signal.

公开(公告)号：US20210074306A1

公开(公告)日：2021-03-11

申请号：US17017413

申请日：2020-09-10

Applicant: Electronics and Telecommunications Research Institute

Inventor： Jongmo SUNG ,  Seung Kwon BEACK ,  Mi Suk LEE ,  Tae Jin LEE ,  Woo-taek LIM ,  Jin Soo CHOI

IPC: G10L19/032 ,  H03M7/30 ,  G06N3/08 ,  G06N5/04

Abstract: Provided are an audio encoding method, an audio decoding method, an audio encoding apparatus, and an audio decoding apparatus using dynamic model parameters. The audio encoding method using dynamic model parameters may use dynamic model parameters corresponding to each of the levels of the encoding network when reducing the dimension of an audio signal in the encoding network. In addition, the audio decoding method using the dynamic model parameter may use a dynamic model parameter corresponding to each of the levels of the decoding network when extending the dimension of an audio signal in an encoding network.

公开(公告)号：US20200382787A1

公开(公告)日：2020-12-03

申请号：US16999208

申请日：2020-08-21

Applicant: Electronics and Telecommunications Research Institute ,  UNIVERSITY-INDUSTRY COOPERATION GROUP OF KYUNG HEE UNIVERSITY

Inventor： Hui Yong KIM ,  Sung Chang LIM ,  Jin Ho LEE ,  Jin Soo CHOI ,  Jin Woong KIM ,  Gwang Hoon PARK ,  Kyung Yong KIM

IPC: H04N19/129 ,  H04N19/176 ,  H04N19/70 ,  H04N19/122 ,  H04N19/159 ,  H04N19/119 ,  H04N19/136 ,  H04N19/61 ,  H04N19/593 ,  H04N19/625 ,  H04N19/124 ,  H04N19/157 ,  H04N19/44

Abstract: A method and a device for encoding/decoding images are disclosed. The method for encoding images comprises the steps of: deriving a scan type of a residual signal for a current block according to whether or not the current block is a transform skip block; and applying the scan type to the residual signal for the current block, wherein the transform skip block is a block to which transform for the current block is not applied and is specified on the basis of information indicating whether or not transform for the current block is to be applied.

公开(公告)号：US20200382786A1

公开(公告)日：2020-12-03

申请号：US16998593

申请日：2020-08-20

Applicant: Electronics and Telecommunications Research Institute ,  UNIVERSITY-INDUSTRY COOPERATION GROUP OF KYUNG HEE UNIVERSITY

Inventor： Hui Yong KIM ,  Sung Chang LIM ,  Jin Ho LEE ,  Jin Soo CHOI ,  Jin Woong KIM ,  Gwang Hoon PARK ,  Kyung Yong KIM

IPC: H04N19/129 ,  H04N19/176 ,  H04N19/70 ,  H04N19/122 ,  H04N19/159 ,  H04N19/119 ,  H04N19/136 ,  H04N19/61 ,  H04N19/593 ,  H04N19/625 ,  H04N19/124 ,  H04N19/157 ,  H04N19/44

Abstract: A method and a device for encoding/decoding images are disclosed. The method for encoding images comprises the steps of: deriving a scan type of a residual signal for a current block according to whether or not the current block is a transform skip block; and applying the scan type to the residual signal for the current block, wherein the transform skip block is a block to which transform for the current block is not applied and is specified on the basis of information indicating whether or not transform for the current block is to be applied.

公开(公告)号：US20200344490A1

公开(公告)日：2020-10-29

申请号：US16927003

申请日：2020-07-13

Applicant: Electronics and Telecommunications Research Institute ,  Industry-University Cooperation Foundation Korea Aerospace University

Inventor： Sung Chang LIM ,  Hui Yong KIM ,  Jin Ho LEE ,  Jin Soo CHOI ,  Jin Woong KIM ,  Jae Gon KIM ,  Sang Yong LEE ,  Un Ki PARK

IPC: H04N19/56 ,  H04N19/70 ,  H04N19/52 ,  H04N19/13 ,  H04N19/593 ,  H04N19/513

Abstract: Disclosed are a method for inducing a prediction motion vector and an apparatus using the same. An image decoding method can include: a step of determining the information related to a plurality of spatial candidate prediction motion vectors from peripheral predicted blocks of a predicted target block; and a step of determining the information related to temporal candidate prediction motion vectors on the basis of the information related to the plurality of spatial candidate prediction motion vectors. Accordingly, the present invention can reduce complexity and can enhance coding efficiency when inducing the optimum prediction motion vector.

公开(公告)号：US20200252638A1

公开(公告)日：2020-08-06

申请号：US16857758

申请日：2020-04-24

Applicant: Electronics and Telecommunications Research Institute ,  KOREA ADVANCED INSTITUTE OF SCIENCE AND TECHNOLOGY

Inventor： Jong Ho KIM ,  Hui Yong KIM ,  Se Yoon JEONG ,  Sung Chang LIM ,  Ha Hyun LEE ,  Jin Ho LEE ,  Suk Hee CHO ,  Jin Soo CHOI ,  Jin Woong KIM ,  Chie Teuk AHN ,  Mun Churl KIM ,  Bum Shik LEE

IPC: H04N19/44 ,  H04N19/70 ,  H04N19/46 ,  H04N19/593 ,  H04N19/60 ,  H04N19/18 ,  H04N19/64

Abstract: Disclosed decoding method of the intra prediction mode comprises the steps of: determining whether an intra prediction mode of a present prediction unit is the same as a first candidate intra prediction mode or as a second candidate intra prediction mode on the basis of 1-bit information; and determining, among said first candidate intra prediction mode and said second candidate intra prediction mode, which candidate intra prediction mode is the same as the intra prediction mode of said present prediction unit on the basis of additional 1-bit information, if the intra prediction mode of the present prediction unit is the same as at least either the first candidate intra prediction mode or the second candidate intra prediction mode, and decoding the intra prediction mode of the present prediction unit.