公开(公告)号：US11978465B2

公开(公告)日：2024-05-07

申请号：US17507746

申请日：2021-10-21

Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE

Inventor： Seung Kwon Beack ,  Jongmo Sung ,  Tae Jin Lee ,  Woo-taek Lim ,  Inseon Jang

IPC: G10L19/13 ,  G10L19/032 ,  G10L19/06

CPC classification number: G10L19/13 ,  G10L19/032 ,  G10L19/06

Abstract: A method of generating a residual signal performed by an encoder includes identifying an input signal including an audio sample, generating a first residual signal from the input signal using linear predictive coding (LPC), generating a second residual signal having a less information amount than the first residual signal by transforming the first residual signal, transforming the second residual signal into a frequency domain, and generating a third residual signal having a less information amount than the second residual signal from the transformed second residual signal using frequency-domain prediction (FDP) coding.

公开(公告)号：US11804230B2

公开(公告)日：2023-10-31

申请号：US17711908

申请日：2022-04-01

Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE ,  Gwangju Institute of Science and Technology

Inventor： Inseon Jang ,  Seung Kwon Beack ,  Jongmo Sung ,  Tae Jin Lee ,  Woo-taek Lim ,  Jongwon Shin ,  Youngju Cheon ,  Sangwook Han ,  Soojoong Hwang

IPC: G10L19/02 ,  G10L19/038 ,  G06N3/04

CPC classification number: G10L19/038 ,  G06N3/04 ,  G10L19/02

Abstract: An audio encoding/decoding apparatus and method using vector quantized residual error features are disclosed. An audio signal encoding method includes outputting a bitstream of a main codec by encoding an original signal, decoding the bitstream of the main codec, determining a residual error feature vector from a feature vector of a decoded signal and a feature vector of the original signal, and outputting a bitstream of additional information by encoding the residual error feature vector.

公开(公告)号：US11508385B2

公开(公告)日：2022-11-22

申请号：US16686859

申请日：2019-11-18

Applicant: Electronics and Telecommunications Research Institute

Inventor： Seung Kwon Beack ,  Jongmo Sung ,  Mi Suk Lee ,  Tae Jin Lee ,  Hui Yong Kim

IPC: G06N3/04 ,  G06N3/08 ,  G10L19/032 ,  G10L19/02

Abstract: Disclosed is a method of processing a residual signal for audio coding and an audio coding apparatus. The method learns a feature map of a reference signal through a residual signal learning engine including a convolutional layer and a neural network and performs learning based on a result obtained by mapping a node of an output layer of the neural network and a quantization level of index of the residual signal.

公开(公告)号：US11488613B2

公开(公告)日：2022-11-01

申请号：US17098090

申请日：2020-11-13

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

Inventor： Minje Kim ,  Kai Zhen ,  Mi Suk Lee ,  Seung Kwon Beack ,  Jongmo Sung ,  Tae Jin Lee ,  Jin Soo Choi

IPC: G10L19/08 ,  G10L19/032 ,  G10L19/26 ,  G06N3/08 ,  G10L25/30 ,  G10L13/02 ,  G10L21/0208

Abstract: Disclosed are a method for coding a residual signal of LPC coefficients based on collaborative quantization and a computing device for performing the method. The residual signal coding method includes: generating encoded LPC coefficients and LPC residual signals by performing LPC analysis and quantization on an input speech; Determining a predicted LPC residual signal by applying the LPC residual signal to cross module residual learning; Performing LPC synthesis using the coded LPC coefficients and the predicted LPC residual signal; It may include the step of determining an output speech that is a synthesized output according to a result of performing the LPC synthesis.

公开(公告)号：US11416742B2

公开(公告)日：2022-08-16

申请号：US16122708

申请日：2018-09-05

Applicant: Electronics and Telecommunications Research Institute ,  THE TRUSTEES OF INDIANA UNIVERSITY

Inventor： Jongmo Sung ,  Minje Kim ,  Aswin Sivaraman ,  Kai Zhen

IPC: G06N3/08 ,  G10L19/008 ,  G10L19/032 ,  G10L25/30 ,  G10L25/69

Abstract: Provided is a training method of a neural network that is applied to an audio signal encoding method using an audio signal encoding apparatus, the training method including generating a masking threshold of a first audio signal before training is performed, calculating a weight matrix to be applied to a frequency component of the first audio signal based on the masking threshold, generating a weighted error function obtained by correcting a preset error function using the weight matrix, and generating a second audio signal by applying a parameter learned using the weighted error function to the first audio signal.

公开(公告)号：US20220020385A1

公开(公告)日：2022-01-20

申请号：US17377157

申请日：2021-07-15

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: G10L19/06 ,  G10L19/032

Abstract: An audio signal encoding method performed by an encoder includes identifying a time-domain audio signal in a unit of blocks, quantizing a linear prediction coefficient extracted from a combined block in which a current original block of the audio signal and a previous original block chronologically adjacent to the current original block using frequency-domain linear predictive coding (LPC), generating a temporal envelope by dequantizing the quantized linear prediction coefficient, extracting a residual signal from the combined block based on the temporal envelope, quantizing the residual signal by one of time-domain quantization and frequency-domain quantization, and transforming the quantized residual signal and the quantized linear prediction coefficient into a bitstream.

公开(公告)号：US20210005208A1

公开(公告)日：2021-01-07

申请号：US16686859

申请日：2019-11-18

Applicant: Electronics and Telecommunications Research Institute

Inventor： Seung Kwon Beack ,  Jongmo Sung ,  Mi Suk Lee ,  Tae Jin Lee ,  Hui Yong Kim

IPC: G10L19/02 ,  G10L19/032 ,  G06N3/08 ,  G06N3/04

Abstract: Disclosed is a method of processing a residual signal for audio coding and an audio coding apparatus. The method learns a feature map of a reference signal through a residual signal learning engine including a convolutional layer and a neural network and performs learning based on a result obtained by mapping a node of an output layer of the neural network and a quantization level of index of the residual signal.