Patents by Inventor Seung Kwon Beack

Seung Kwon Beack has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Publication number: 20250104721
    Abstract: Disclosed are a device and method for audio signal processing. The audio signal processing device according to an embodiment includes a receiver configured to receive a bitstream corresponding to a compressed audio signal and a processor. The processor may be configured to generate a real restoration signal or a complex restoration signal by performing inverse quantization on real data of the bitstream or complex data of the bitstream, generate a result of real Frequency Domain Noise Shaping (FDNS) synthesis or a result of complex FDNS synthesis by performing FDNS synthesis on the real restoration signal or the complex restoration signal, and generate a restored audio signal by performing frequency-to-time transform on the result of the real FDNS synthesis or the result of the complex FDNS synthesis.
    Type: Application
    Filed: December 15, 2022
    Publication date: March 27, 2025
    Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE
    Inventors: Seung Kwon BEACK, Jongmo SUNG, Tae Jin LEE, Woo-taek LIM, Inseon JANG, Byeongho CHO
  • Publication number: 20250104724
    Abstract: A method and apparatus for encoding/decoding a neural network-based personalized speech are provided. The method includes outputting a first bit stream in which an input speech signal is encrypted, based on the input speech signal, and outputting a second bit stream in which speaker information of the input speech signal is encrypted, based on the input speech signal.
    Type: Application
    Filed: September 16, 2024
    Publication date: March 27, 2025
    Applicants: Electronics and Telecommunications Research Institute, The Trustees of Indiana University
    Inventors: Inseon JANG, Soo Young PARK, Seung Kwon BEACK, Jongmo SUNG, Woo-taek LIM, Byeongho CHO, Jung Won KANG, Tae Jin LEE, Minje KIM, Haici YANG
  • Publication number: 20250104722
    Abstract: A method and device for encoding/decoding an audio signal based on dequantization through potential diffusion are provided. The method of decoding an audio signal includes obtaining a discrete latent vector in which a speech signal is quantized and based on the discrete latent vector, outputting a continuous latent vector in which the discrete latent vector is dequantized.
    Type: Application
    Filed: September 16, 2024
    Publication date: March 27, 2025
    Applicants: Electronics and Telecommunications Research Institute, The Trustees of Indiana University
    Inventors: Inseon JANG, Woo-taek LIM, Soo Young PARK, Seung Kwon BEACK, Jongmo SUNG, Byeongho CHO, Jung Won KANG, Tae Jin LEE, Minje KIM, Haici YANG
  • Publication number: 20250069609
    Abstract: An encoding apparatus and a decoding apparatus in a transform between a Modified Discrete Cosine Transform (MDCT)-based coder and a different coder are provided. The encoding apparatus may encode additional information to restore an input signal encoded according to the MIDCT-based coding scheme, when switching occurs between the MDCT-based coder and the different coder. Accordingly, an unnecessary bitstream may be prevented from being generated, and minimum additional information may be encoded.
    Type: Application
    Filed: November 15, 2024
    Publication date: February 27, 2025
    Applicants: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE, KWANGWOON UNIVERSITY INDUSTRY-ACADEMIC COLLABORATION FOUNDATION
    Inventors: Seung Kwon BEACK, Tae Jin LEE, Min Je KIM, Dae Young JANG, Kyeongok KANG, Jin Woo HONG, Ho Chong PARK, Young-cheol PARK
  • Patent number: 12231864
    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.
    Type: Grant
    Filed: December 1, 2023
    Date of Patent: February 18, 2025
    Assignee: Electronics and Telecommunications Research Institute
    Inventors: Yong Ju Lee, Jeong Il Seo, Seung Kwon Beack, Kyeong Ok Kang, Jin Woong Kim, Jae Hyoun Yoo
  • Patent number: 12223970
    Abstract: An encoding method, a decoding method, an encoder for performing the encoding method, and a decoder for performing the decoding method are provided. The encoding method includes outputting LP coefficients bitstream and a residual signal by performing an LP analysis on an input signal, outputting a first latent signal obtained by encoding a periodic component of the residual signal, a second latent signal obtained by encoding a non-periodic component of the residual signal, and a weight vector for each of the first latent signal and the second latent signal, using a first neural network module, and outputting a first bitstream obtained by quantizing the first latent signal, a second bitstream obtained by quantizing the second latent signal, and a weight bitstream obtained by quantizing the weight vector, using a quantization module.
    Type: Grant
    Filed: January 31, 2023
    Date of Patent: February 11, 2025
    Assignee: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE
    Inventors: Jongmo Sung, Seung Kwon Beack, Tae Jin Lee, Woo-taek Lim, Inseon Jang, Byeongho Cho
  • Patent number: 12223426
    Abstract: Provided is a method and apparatus for designing and testing an audio codec using quantization based on white noise modeling. A neural network-based audio encoder design method includes generating a quantized latent vector and a reconstructed signal corresponding to an input signal by using a white noise modeling-based quantization process, computing a total loss for training a neural network-based audio codec, based on the input signal, the reconstruction signal, and the quantized latent vector, training the neural network-based audio codec by using the total loss, and validating the trained neural network-based audio codec to select the best neural network-based audio codec.
    Type: Grant
    Filed: February 8, 2023
    Date of Patent: February 11, 2025
    Assignees: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE, YONSEI UNIVERSITY WONJU INDUSTRY-ACADEMIC COOPERATION FOUNDATION
    Inventors: Jongmo Sung, Seung Kwon Beack, Tae Jin Lee, Woo-taek Lim, Inseon Jang, Byeongho Cho, Young Cheol Park, Joon Byun, Seungmin Shin
  • Patent number: 12205605
    Abstract: An audio signal encoding and decoding method using a neural network model, and an encoder and decoder for performing the same are disclosed. A method of encoding an audio signal using a neural network model, the method may include identifying an input signal, generating a quantized latent vector by inputting the input signal into a neural network model encoding the input signal, and generating a bitstream corresponding to the quantized latent vector, wherein the neural network model may include i) a feature extraction layer generating a latent vector by extracting a feature of the input signal, ii) a plurality of downsampling blocks downsampling the latent vector, and iii) a plurality of quantization blocks performing quantization of a downsampled latent vector.
    Type: Grant
    Filed: February 11, 2022
    Date of Patent: January 21, 2025
    Assignees: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE, INDUSTRY-ACADEMIC COOPERATION FOUNDATION, YONSEI UNIVERSITY
    Inventors: Inseon Jang, Seung Kwon Beack, Jongmo Sung, Tae Jin Lee, Woo-Taek Lim, Hong-Goo Kang, Jihyun Lee, Chanwoo Lee, Hyungseob Lim
  • Publication number: 20250006210
    Abstract: A method of encoding/decoding a speech signal and a device for performing the same are provided. The method includes outputting, based on a first input speech signal of a previous timepoint and a second input speech signal of a current timepoint, a predicted signal that predicts the second input speech signal from the first input speech signal and obtaining, based on the second input speech signal and the predicted signal, a residual signal by removing a correlation between the first input speech signal and the second input speech signal from the second input speech signal.
    Type: Application
    Filed: June 18, 2024
    Publication date: January 2, 2025
    Applicants: Electronics and Telecommunications Research Institute, UIF (University Industry Foundation), Yonsei University
    Inventors: Woo-taek LIM, Inseon JANG, Seung Kwon BEACK, Hong-Goo KANG, Byeong Hyeon KIM, Jihyun LEE, Hyungseob LIM
  • Publication number: 20240420712
    Abstract: A method of encoding/decoding an audio signal and a device for performing the same are provided. The method of encoding an audio signal includes generating, based on the audio signal, a linear prediction coding (LPC) bitstream and a frequency-domain signal of the audio signal, generating, based on the LPC bitstream and the frequency-domain signal, a first residual signal including information on a frequency envelope of the frequency-domain signal, and outputting a second residual signal by processing a first residual signal through one of a plurality of signal processing paths.
    Type: Application
    Filed: June 4, 2024
    Publication date: December 19, 2024
    Applicant: Electronics and Telecommunications Research Institute
    Inventors: Byeongho CHO, Seung Kwon BEACK, Jung Won KANG, Soo Young PARK, Jongmo SUNG, Tae Jin LEE, Woo-taek LIM, Inseon JANG
  • Patent number: 12159640
    Abstract: Provided is an encoding method according to various example embodiments and an encoder performing the method. The encoding method includes outputting a linear prediction (LP) coefficients bitstream and a residual signal by performing a linear prediction analysis on an input signal, outputting a first latent signal obtained by encoding a periodic component of the residual signal, using a first neural network module, outputting a first bitstream obtained by quantizing the first latent signal, using a quantization module, outputting a second latent signal obtained by encoding an aperiodic component of the residual signal, using the first neural network module, and outputting a second bitstream obtained by quantizing the second latent signal, using the quantization module, wherein the aperiodic component of the residual signal is calculated based on a periodic component of the residual signal decoded from the quantized first latent signal output by de-quantizing the first bitstream.
    Type: Grant
    Filed: August 9, 2022
    Date of Patent: December 3, 2024
    Assignee: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE
    Inventors: Jongmo Sung, Seung Kwon Beack, Tae Jin Lee, Woo-taek Lim, Inseon Jang
  • Patent number: 12148438
    Abstract: An encoding apparatus and a decoding apparatus in a transform between a Modified Discrete Cosine Transform (MDCT)-based coder and a different coder are provided. The encoding apparatus may encode additional information to restore an input signal encoded according to the MDCT-based coding scheme, when switching occurs between the MDCT-based coder and the different coder. Accordingly, an unnecessary bitstream may be prevented from being generated, and minimum additional information may be encoded.
    Type: Grant
    Filed: July 12, 2021
    Date of Patent: November 19, 2024
    Assignees: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE, KWANGWOON UNIVERSITY INDUSTRY-ACADEMIC COLLABORATION FOUNDATION
    Inventors: Seung Kwon Beack, Tae Jin Lee, Min Je Kim, Dae Young Jang, Kyeongok Kang, Jin Woo Hong, Ho Chong Park, Young-cheol Park
  • Publication number: 20240371383
    Abstract: A method and apparatus for encoding/decoding audio signal are provided. The encoding method includes transforming an input audio signal in a time domain into an audio signal in a frequency domain, quantizing energy of a frequency band of the audio signal in the frequency domain, generating a normal signal by normalizing the audio signal in the frequency domain according to quantized energy, obtaining a feature vector including information on the energy of the frequency band based on the normal signal and the input audio signal, quantizing the feature vector, obtaining a scale factor used to scale the normal signal based on the quantized feature vector, quantizing an adjustment signal into which the normal signal has been scaled based on the scale factor, and outputting bitstreams based on the quantized energy, the quantized feature vector, and the quantized adjustment signal.
    Type: Application
    Filed: May 2, 2024
    Publication date: November 7, 2024
    Applicants: Electronics and Telecommunications Research Institute, UIF (University Industry Foundation), Yonsei University
    Inventors: Inseon JANG, Seung Kwon BEACK, Jongmo SUNG, Tae Jin LEE, Woo-taek LIM, Byeongho CHO, Hong-Goo KANG, Byeong Hyeon KIM, Jihyun LEE, Hyungseob LIM
  • Publication number: 20240290335
    Abstract: Disclosed are an audio signal encoding/decoding method and an apparatus for performing the same. An audio signal encoding method includes receiving a current frame signal and a reconstructed previous frame signal, generating a predicted current frame signal, based on the current frame signal and the reconstructed previous frame signal, and outputting a reconstructed residual signal, based on the current frame signal and the predicted current frame signal.
    Type: Application
    Filed: February 7, 2024
    Publication date: August 29, 2024
    Applicant: Electronics and Telecommunications Research Institute
    Inventors: Seung Kwon BEACK, Byeongho CHO
  • Publication number: 20240233738
    Abstract: Provided is an encoding apparatus including a memory configured to store instructions and a processor electrically connected to the memory and configured to execute the instructions, wherein the processor may be configured to perform a plurality of operations, when the instructions are executed by the processor, wherein the plurality of operations may include obtaining an input audio signal, generating an embedded audio signal by embedding signal components of a second frequency band of the input audio signal in a first frequency band of the input audio signal, generating additional information associated with the first frequency band and the second frequency band, generating an encoded audio signal by encoding the embedded audio signal, and formatting the encoded audio signal and the additional information into a bitstream.
    Type: Application
    Filed: July 25, 2023
    Publication date: July 11, 2024
    Applicants: Electronics and Telecommunications Research Institute, Gwangju Institute of Science and Technology
    Inventors: Inseon JANG, Seung Kwon BEACK, Tae Jin LEE, Jongmo SUNG, Woo-taek LIM, Byeongho CHO, Jongwon SHIN
  • Publication number: 20240169997
    Abstract: An audio signal processing method, which is executed by a processor electronically communicating with a deep neural network within a computing system, may comprise: acquiring, by the processor, an input signal before encoding and an output signal after quantization and decoding; calculating, by the processor, a perceptual global loss for a frame corresponding to the input and the output signals; acquiring, by the processor, a plurality of subframes corresponding to the input and output signals by applying a windowing function to the frame of the input and output signals; calculating, by the processor, perceptual local losses for the plurality of subframes corresponding to the input and output signals; and acquiring, by the processor, multi-time scale perceptual loss based on the perceptual global and local losses.
    Type: Application
    Filed: November 9, 2023
    Publication date: May 23, 2024
    Inventors: Jong Mo SUNG, Seung Kwon BEACK, Young Cheol Park, Joon BYUN, Seung Min SHIN
  • Publication number: 20240153513
    Abstract: A complex number quantization-based audio signal encoding method may comprise: estimating a scale factor for each subband of an input audio signal; performing complex magnitude scaling for each subband based on the scale factor; and performing polar quantization on a complex frequency coefficient for each subband, wherein the performing the polar quantization for each subband comprises applying two or more different magnitude quantization techniques based on the magnitude of the complex frequency coefficient scaled for each subband.
    Type: Application
    Filed: November 6, 2023
    Publication date: May 9, 2024
    Applicant: Electronics and Telecommunications Research Institute
    Inventors: Byeong Ho CHO, Seung Kwon BEACK, Jong Mo SUNG, Tae Jin LEE, Woo Taek LIM, In Seon JANG
  • Patent number: 11978465
    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.
    Type: Grant
    Filed: October 21, 2021
    Date of Patent: May 7, 2024
    Assignee: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE
    Inventors: Seung Kwon Beack, Jongmo Sung, Tae Jin Lee, Woo-taek Lim, Inseon Jang
  • Publication number: 20240144943
    Abstract: An audio signal encoding/decoding method and an apparatus for performing the same are disclosed. The audio signal encoding method includes obtaining a full-band input signal, extracting a first feature vector corresponding to a first sub-band signal and a second feature vector corresponding to a second sub-band signal using an encoder neural network including a plurality of encoding layers, generating a first code vector corresponding to the first feature vector and a second code vector corresponding to the second feature vector by compressing the first feature vector and the second feature vector, and generating a bitstream by quantizing the first code vector and the second code vector.
    Type: Application
    Filed: September 25, 2023
    Publication date: May 2, 2024
    Applicants: Electronics and Telecommunications Research Institute, The Trustees of Indiana University
    Inventors: Woo-taek LIM, Seung Kwon BEACK, Inseon JANG, Jongmo SUNG, Tae Jin LEE, Byeongho CHO, Minje KIM, Darius Petermann
  • Publication number: 20240135941
    Abstract: Provided is an encoding apparatus including a memory configured to store instructions and a processor electrically connected to the memory and configured to execute the instructions, wherein the processor may be configured to perform a plurality of operations, when the instructions are executed by the processor, wherein the plurality of operations may include obtaining an input audio signal, generating an embedded audio signal by embedding signal components of a second frequency band of the input audio signal in a first frequency band of the input audio signal, generating additional information associated with the first frequency band and the second frequency band, generating an encoded audio signal by encoding the embedded audio signal, and formatting the encoded audio signal and the additional information into a bitstream.
    Type: Application
    Filed: July 24, 2023
    Publication date: April 25, 2024
    Applicants: Electronics and Telecommunications Research Institute, Gwangju Institute of Science and Technology
    Inventors: Inseon JANG, Seung Kwon BEACK, Tae Jin LEE, Jongmo SUNG, Woo-taek LIM, Byeongho CHO, Jongwon SHIN