Electronics and Telecommunications Research Institute

Indiana University

Kwangwoon University Industry-Academic Collaboration Foundation

Mi Suk Lee

Tae Jin Lee

Seung Kwon Beack

Jongmo Sung

Woo-taek Lim

Jin Soo Choi

Inseon Jang

Minje Kim

Kai Zhen

Hui Yong Kim

Dae Young Jang

Hochong Park

Yong Ju Lee

Kyeongok Kang

Byung Sun Lee

In Ki Hwang

Jong Mo Sung

Do Young Kim

Dae Ho Kim

Jae-hyoun Yoo

Seung Il Myong

Hyoung Soo Lim

Hyun Joo Bae

Woo Sug Jung

Kyu Tae Yang

Bong Ho Lee

Seong-Hyeon Shin

Haici Yang

The encoding method includes computing the first feature information of an input signal using a recurrent encoding model, quantizing the first feature information and producing the first feature bitstream, computing the first output signal from the quantized first feature information using a recurrent decoding model, computing the second feature information of the input signal using a nonrecurrent encoding model, quantizing the second feature information and producing the second feature bitstream, computing the second output signal from the quantized second feature information using a nonrecurrent decoding model, determining an encoding mode based on the input signal, the first and second output signals, and the first and second feature bitstreams, and outputting an overall bitstream by multiplexing an encoding mode bit and one of the first feature bitstream and the second feature bitstream depending on the encoding mode.

Methods of encoding and decoding audio signal using neural network model, and devices for performing the methods

Disclosed is an apparatus and method for audio encoding/decoding that is robust against coding distortion in a transition section. An audio encoding method includes outputting a frequency domain signal by time-to-frequency (T/F) transform of an input signal, outputting a frequency domain residual signal in which a frequency axis envelope is removed from the frequency domain signal by applying frequency domain noise shaping (FDNS) encoding to the frequency domain signal, outputting a time domain residual signal in which a time axis envelope is removed by performing linear prediction coefficient (LPC) analysis based on the frequency domain residual signal, and quantizing and transmitting the time domain residual signal.

Apparatus and method for audio encoding/decoding robust to transition segment encoding distortion

An audio signal encoding and decoding method using a neural network model, a method of training the neural network model, and an encoder and decoder performing the methods are disclosed. The encoding method includes computing the first feature information of an input signal using a recurrent encoding model, computing an output signal from the first feature information using a recurrent decoding model, calculating a residual signal by subtracting the output signal from the input signal, computing the second feature information of the residual signal using a nonrecurrent encoding model, and converting the first feature information and the second feature information to a bitstream.

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.

Apparatus and method for speech processing using a densely connected hybrid neural network

A method and apparatus for processing an audio signal are disclosed. According to an example embodiment, a method of processing an audio signal may include acquiring a final audio signal for an initial audio signal using a plurality of neural network models generating output audio signals by encoding and decoding input audio signals, calculating a difference between the initial audio signal and the final audio signal in a time domain, converting the initial audio signal and the final audio signal into Mel-spectra, calculating a difference between the Mel-spectra of the initial audio signal and the final audio signal in a frequency domain, training the plurality of neural network models based on results calculated in the time domain and the frequency domain, and generating a new final audio signal distinguished from the final audio signal from the initial audio signal using the trained neural network models.

Method and apparatus for processing audio signal

Provided is a digital twin disaster management system customized to keep safety for urban underground tunnels, including: a sensor sub-system configured to detect environmental information, status information and image information in the urban underground tunnels; a digital twin model management sub-system configured to create and update a virtual space corresponding to the urban underground tunnels using information provided from the sensor sub-system and 3D space, insert various types of attributes into the virtual space, detect tagging information, predict the spread of each disaster, and infer a degree of risk of a management facility; a disaster management sub-system having a control function of conducting centralized supervision by displaying information about components installed in the urban underground tunnels in the metaverse space and recording a situation; and a network sub-system configured to provide the virtual space to a user terminal of an external inspector.

Digital twin disaster management system customized for underground public areas

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.

Methods of encoding and decoding speech signal using neural network model recognizing sound sources, and encoding and decoding apparatuses for performing the same

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.

Apparatus and method for encoding/decoding audio signal using information of previous frame

An audio signal encoding method performed by an encoder includes identifying an audio signal of a time domain in units of a block, generating a combined block by combining i) a current original block of the audio signal and ii) a previous original block chronologically adjacent to the current original block, extracting a first residual signal of a frequency domain from the combined block using linear predictive coding of a time domain, overlapping chronologically adjacent first residual signals among first residual signals converted into a time domain, and quantizing a second residual signal of a time domain extracted from the overlapped first residual signal by converting the second residual signal of the time domain into a frequency domain using linear predictive coding of a frequency domain.

Method and apparatus for encoding and decoding audio signal to reduce quantization noise

A method and apparatus for performing binaural rendering of an audio signal are provided. The method includes identifying an input signal that is based on an object, and metadata that includes distance information indicating a distance to the object, generating a binaural filter that is based on the metadata, using a binaural room impulse response, obtaining a binaural filter to which a low-pass filter (LPF) is applied, using a frequency response control that is based on the distance information, and generating a binaural-rendered output signal by performing a convolution of the input signal and the binaural filter to which the LPF is applied.

Method and apparatus for performing binaural rendering of audio signal

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.

Method of encoding and decoding audio signal using linear predictive coding and encoder and decoder performing the method

An inventive concept relates to an audio coding method to which CNN-based frequency spectrum recovery is applied. An inventive concept transmits a part of frequency spectral coefficients generated in transform coding to a decoder and the decoder recovers the frequency spectral coefficient not transmitted. Furthermore, the signs of frequency spectral coefficient are transmitted from an encoder to the decoder depending on a sign transmission rule.

Audio coding method based on spectral recovery scheme

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.

Method of processing residual signal for audio coding, and audio processing apparatus

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.

Residual coding method of linear prediction coding coefficient based on collaborative quantization, and computing device for performing the method

Disclosed are a method of encoding a high band of an audio, a method of decoding a high band of an audio, and an encoder and a decoder for performing the methods. The method of decoding a high band of an audio, the method performed by a decoder, includes identifying a parameter extracted through a first neural network, identifying side information extracted through a second neural network, and restoring a high band of an audio by applying the parameter and the side information to a third neural network.

Growing community of inventors

Daejeon, South Korea

Mi Suk Lee