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.

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.

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.

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.

Abstract: 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.

Abstract: Provided are an apparatus for encoding an audio signal and a method of an operation thereof. An audio signal encoding method includes obtaining quantized linear prediction (LP) coefficients by performing a linear predictive coding (LPC) analysis and quantization on an input audio signal, generating a reference signal by applying discrete Fourier transform (DFT) to the input audio signal, obtaining LP residual coefficients from the reference signal, scaling magnitudes of the LP residual coefficients using the quantized LP coefficients and the reference signal, and quantizing phases of the LP residual coefficients and the scaled magnitudes of the LP residual coefficients.

Abstract: A method, executed by a processor for compressing an audio signal in multiple layers, may comprise: (a) restoring, in a highest layer, an input audio signal as a first signal; (b) restoring, in at least one intermediate layer, a signal obtained by subtracting an upsampled signal, which is obtained by upsampling the audio signal restored in the highest layer or an immediately previous intermediate layer, from the input audio signal as a second signal; and (c) restoring, in a lowest layer, a signal obtained by subtracting an upsampled signal, which is obtained by upsampling the audio signal restored in an intermediate layer immediately before the lowest layer, from the input audio signal as a third signal, wherein the first signal, the second signal, and the third signal are combined to output a final restoration audio signal.

Abstract: A method of encoding a speech signal includes predicting a feature vector of each of a plurality of frames included in the speech signal based on a ground-truth feature vector of a previous frame of each of the plurality of frames, calculating a residual signal corresponding to each of the plurality of frames based on a ground-truth feature vector of each of the plurality of frames and a predicted feature vector of each of the plurality of frames, and generating a bitstring corresponding to each of the plurality of frames by quantizing the residual signal.

Abstract: 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.

Abstract: Disclosed are a method of encoding and decoding an audio signal and an encoder and a decoder performing the method. The method of encoding an audio signal includes identifying an input signal, and generating a bitstring of each encoding layer by applying, to the input signal, an encoding model including a plurality of successive encoding layers that encodes the input signal, in which a current encoding layer among the encoding layers is trained to generate a bitstring of the current encoding layer by encoding an encoded signal which is a signal encoded in a previous encoding layer and quantizing an encoded signal which is a signal encoded in the current encoding layer.

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.

Abstract: A signal compression method and apparatus and a signal restoration method and apparatus are provided. The signal compression method includes outputting an input signal, obtained by processing an audio signal, which is input, based on a human auditory perception characteristic, using an auditory perception model, extracting a feature vector from the input signal using a feature extraction module, and outputting a code obtained by compressing the feature vector using a trained signal compression model.

Abstract: Disclosed are methods of encoding and decoding an audio signal using side information, and an encoder and a decoder for performing the methods. The method of encoding an audio signal using side information includes identifying an input signal, the input signal being an original audio signal, extracting side information from the input signal using a learning model trained to extract side information from a feature vector of the input signal, encoding the input signal, and generating a bitstream by combining the encoded input signal and the side information.

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.

Abstract: A method for encoding an input signal using N flow blocks (N is a natural number greater than or equal to 2) and (N?1) split block(s), which is performed by a processor, may comprise: transmitting, by a k-th flow block (k is a natural number greater than or equal to 1 and less than or equal to N?1) among the N flow blocks, a k-th transformation signal obtained by transforming a received signal into a latent representation to a k-th split block among the (N?1) split block(s); splitting, by the k-th split block, the k-th transformation signal by a predetermined ratio, into a first split signal and a second split signal; transmitting, by the k-th split block, the first split signal to a (k+1)-th flow block; and quantizing a signal transformed by an N-th flow block and the second split signals using a quantization block.

Abstract: An encoding method and an encoding device using a complex signal and a decoding method and a decoding device using a complex signal are provided. The encoding method includes converting a first channel signal and a second channel signal constituting an audio signal corresponding to a stereo signal from a real domain to a complex domain, determining one of a sum operation, a difference operation, and a bypass operation to be performed on the second channel signal converted to the complex domain, determining a complex spatial cue according to the determined operation, converting a residual signal for the second channel signal to a real domain using the complex spatial cue, converting the first channel signal to a real domain, encoding the first channel signal converted to the real domain, and encoding the residual signal for the second channel signal converted to the real domain.

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.

Abstract: A method, executed by a processor for compressing an audio signal in multiple layers, may comprise: (a) restoring, in a highest layer, an input audio signal as a first signal; (b) restoring, in at least one intermediate layer, a signal obtained by subtracting an upsampled signal, which is obtained by upsampling the audio signal restored in the highest layer or an immediately previous intermediate layer, from the input audio signal as a second signal; and (c) restoring, in a lowest layer, a signal obtained by subtracting an upsampled signal, which is obtained by upsampling the audio signal restored in an intermediate layer immediately before the lowest layer, from the input audio signal as a third signal, wherein the first signal, the second signal, and the third signal are combined to output a final restoration audio signal.

Abstract: A generative adversarial network-based audio signal generation model for generating a high quality audio signal may comprise: a generator generating an audio signal with an external input; a harmonic-percussive separation model separating the generated audio signal into a harmonic component signal and a percussive component signal; and at least one discriminator evaluating whether each of the harmonic component signal and the percussive component signal is real or fake.

Abstract: Provided are an encoding method, an encoding device, a decoding method, and a decoding device using a scalar quantization and a vector quantization. The encoding method includes converting an input signal of a time domain into a frequency domain, generating a first residual signal from an input signal of a frequency domain by using a scale factor, performing a scalar quantization of the first residual signal, generating a second residual signal from the scalar-quantized first residual signal, performing a lossless encoding of the scalar-quantized first residual signal, performing a vector quantization of the second residual signal, and transmitting a bitstream including the lossless-encoded first residual signal and the vector-quantized second residual signal.