公开(公告)号：US12205605B2

公开(公告)日：2025-01-21

申请号：US17670172

申请日：2022-02-11

Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE ,  INDUSTRY-ACADEMIC COOPERATION FOUNDATION, YONSEI UNIVERSITY

Inventor： Inseon Jang ,  Seung Kwon Beack ,  Jongmo Sung ,  Tae Jin Lee ,  Woo-Taek Lim ,  Hong-Goo Kang ,  Jihyun Lee ,  Chanwoo Lee ,  Hyungseob Lim

IPC: G10L19/038 ,  G10L19/00 ,  G10L25/30

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.

公开(公告)号：US11657325B2

公开(公告)日：2023-05-23

申请号：US16927691

申请日：2020-07-13

Applicant: Electronics and Telecommunications Research Institute ,  Kyungpook National University Industry-Academic Cooperation Foundation

Inventor： Young Ho Jeong ,  Soo Young Park ,  Sang Won Suh ,  Woo-Taek Lim ,  Minhan Kim ,  Seokjin Lee

IPC: G06N20/00 ,  G06F17/18

CPC classification number: G06N20/00 ,  G06F17/18

Abstract: Disclosed is an apparatus and method for augmenting training data using a notch filter. The method may include obtaining original data, and obtaining training data having a modified frequency component from the original data by filtering the original data using a filter configured to remove a component of a predetermined frequency band.

公开(公告)号：US11581000B2

公开(公告)日：2023-02-14

申请号：US17105835

申请日：2020-11-27

Applicant: Electronics and Telecommunications Research Institute

Inventor： Woo-Taek Lim ,  Seung Kwon Beack ,  Jongmo Sung ,  Mi Suk Lee ,  Tae Jin Lee

IPC: G10L19/00 ,  G10L25/30 ,  G10L19/16 ,  G06N3/08 ,  G10L19/038

Abstract: Disclosed is an apparatus and method for encoding/decoding an audio signal using information of a previous frame. An audio signal encoding method includes: generating a current latent vector by reducing dimension of a current frame of an audio signal; generating a concatenation vector by concatenating a previous latent vector generated by reducing dimension of a previous frame of the audio signal with the current latent vector; and encoding and quantizing the concatenation vector.