公开(公告)号：US20220375483A1

公开(公告)日：2022-11-24

申请号：US17520895

申请日：2021-11-08

Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE

Inventor： Woo-taek LIM ,  Seung Kwon BEACK ,  Jongmo SUNG ,  Tae Jin LEE ,  Inseon JANG ,  Jong-won SEOK ,  YUNSU KIM

IPC: G10L19/038 ,  G10L19/16 ,  G10L25/30

Abstract: Disclosed are methods of encoding and decoding an audio signal, and an encoder and a decoder for performing the methods. The method of encoding an audio signal includes identifying an input signal corresponding to a low frequency band of the audio signal, windowing the input signal, generating a first latent vector by inputting the windowed input signal to a first encoding model, transforming the windowed input signal into a frequency domain, generating a second latent vector by inputting the transformed input signal to a second encoding model, generating a final latent vector by combining the first latent vector and the second latent vector, and generating a bitstream corresponding to the final latent vector.

公开(公告)号：US20210366497A1

公开(公告)日：2021-11-25

申请号：US17326035

申请日：2021-05-20

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

Inventor： Woo-taek LIM ,  Seung Kwon BEACK ,  Jongmo SUNG ,  Mi Suk LEE ,  Tae Jin LEE ,  Inseon JANG ,  Minje KIM ,  Haici YANG

IPC: G10L19/032

Abstract: Methods of encoding and decoding a speech signal using a neural network model that recognizes sound sources, and encoding and decoding apparatuses for performing the methods are provided. A method of encoding a speech signal includes identifying an input signal for a plurality of sound sources; generating a latent signal by encoding the input signal; obtaining a plurality of sound source signals by separating the latent signal for each of the plurality of sound sources; determining a number of bits used for quantization of each of the plurality of sound source signals according to a type of each of the plurality of sound sources; quantizing each of the plurality of sound source signals based on the determined number of bits; and generating a bitstream by combining the plurality of quantized sound source signals.

公开(公告)号：US20190287550A1

公开(公告)日：2019-09-19

申请号：US16196356

申请日：2018-11-20

Applicant: Electronics and Telecommunications Research Institute

Inventor： Woo-taek LIM

IPC: G10L21/14 ,  G10L21/12 ,  G10L25/30

Abstract: Disclosed is a sound event detecting method including receiving an audio signal, transforming the audio signal into a two-dimensional (2D) signal, extracting a feature map by training a convolutional neural network (CNN) using the 2D signal, pooling the feature map based on a frequency, and determining whether a sound event occurs with respect to each of at least one time interval based on a result of the pooling.