Abstract: An aspect of the present invention provides a learning device including: a neural network that converts an acoustic time series that is a time series representing a sound into feature data expressed in a predetermined format required by a downstream task; and an update unit that updates the neural network on the basis of an execution result of the downstream task using the feature data, in which the neural network includes: a feature extraction unit that converts an input acoustic time series into an intermediate feature tensor that is a third-order tensor indicating features of the acoustic time series and is a tensor having time, frequency, and channel; and an intermediate network that executes processing of converting a representation of the intermediate feature tensor into a representation of a second-order tensor having time and direct product amounts that are amounts indicating a direct product of frequency and channel, and processing of acquiring, for each direct product amount of the second-order tens

Abstract: A coding method and a decoding method are provided which can use in combination a predictive coding and decoding method which is a coding and decoding method that can accurately express coefficients which are convertible into linear prediction coefficients with a small code amount and a coding and decoding method that can obtain correctly, by decoding, coefficients which are convertible into linear prediction coefficients of the present frame if a linear prediction coefficient code of the present frame is correctly input to a decoding device.

Abstract: An autocorrelation calculation unit 21 calculates an autocorrelation RO(i) from an input signal. A prediction coefficient calculation unit 23 performs linear prediction analysis by using a modified autocorrelation R?O(i) obtained by multiplying a coefficient wO(i) by the autocorrelation RO(i). It is assumed here, for each order i of some orders i at least, that the coefficient wO(i) corresponding to the order i is in a monotonically increasing relationship with an increase in a value that is negatively correlated with a fundamental frequency of the input signal of the current frame or a past frame.

Abstract: A coding method and a decoding method are provided which can use in combination a predictive coding and decoding method which is a coding and decoding method that can accurately express coefficients which are convertible into linear prediction coefficients with a small code amount and a coding and decoding method that can obtain correctly, by decoding, coefficients which are convertible into linear prediction coefficients of the present frame if a linear prediction coefficient code of the present frame is correctly input to a decoding device.

Abstract: A learning device includes: spectrogram generation circuitry 1 that generates a spectrogram from an input sound signal; patch generation circuitry 2 that divides the generated spectrogram to generate a plurality of patches; a mask processing circuitry 3 that selects some patches as masked patches; reconstruction circuitry 4 that obtains a plurality of reconstructed patches by reconstructing the plurality of patches by processing of an encoder and a decoder in a transformer serving as a deep learning model by using visible patches other than the masked patches among the plurality of patches and mask tokens corresponding to the masked patches; and parameter update circuitry 5 that updates a parameter of the encoder and a parameter of the decoder such that the masked patches approach reconstructed patches corresponding to the masked patches. The number of layers of the decoder is three or more.

Abstract: A learning device includes: spectrogram generation circuitry 1 that generates a spectrogram from a first sound signal and generates a target spectrogram from a second sound signal; patch generation circuitry 2 that divides the spectrogram to generate a plurality of patches and divides the target spectrogram to generate a plurality of target patches; mask processing circuitry 3 that selects some patches as masked patches; reconstruction circuitry 4 that obtains a plurality of reconstructed patches by reconstructing the plurality of patches by processing of an encoder and a decoder by using visible patches other than some patches among the plurality of patches and mask tokens; and parameter update circuitry 5 that updates parameters such that target patches corresponding to the masked patches among the plurality of target patches approach reconstructed patches corresponding to the masked patches among the plurality of reconstructed patches.

Abstract: An autocorrelation calculation unit 21 calculates an autocorrelation RO(i) from an input signal. A prediction coefficient calculation unit 23 performs linear prediction analysis by using a modified autocorrelation R?O(i) obtained by multiplying a coefficient wO(i) by the autocorrelation RO(i). It is assumed here, for each order i of some orders i at least, that the coefficient wO(i) corresponding to the order i is in a monotonically increasing relationship with an increase in a value that is negatively correlated with a fundamental frequency of the input signal of the current frame or a past frame.

Abstract: Provided is an abnormality estimation device capable of appropriately determining normal data appearing less frequently as normal. The abnormality estimation device includes an estimation unit that estimates an anomaly degree of an acoustic signal, by using an abnormality estimation model that is optimized while using a set of normal sounds and is optimized so as to minimize a difference between an anomaly degree of a normal sound appearing more frequently and an anomaly degree of a normal sound appearing less frequently.

Abstract: An aspect of the present invention provides a learning device including: a neural network that converts an acoustic time series that is a time series representing a sound into feature data expressed in a predetermined format required by a downstream task; and an update unit that updates the neural network on the basis of an execution result of the downstream task using the feature data, in which the neural network includes: a feature extraction unit that converts an input acoustic time series into an intermediate feature tensor that is a third-order tensor indicating features of the acoustic time series and is a tensor having time, frequency, and channel; and an intermediate network that executes processing of converting a representation of the intermediate feature tensor into a representation of a second-order tensor having time and direct product amounts that are amounts indicating a direct product of frequency and channel, and processing of acquiring, for each direct product amount of the second-order tens

Abstract: According to an aspect of the present invention, there is provided a sound estimation model acquisition device including a model acquisition unit configured to acquire a mathematical model that estimates an estimated time series that is a time series satisfying a predetermined estimation condition from one or a plurality of time series on a basis of a first sound time series that is a time series indicating a first sound, a second sound time series that is a time series indicating a second sound, and first difference information indicating at least a partial difference between the first sound and the second sound, in which the mathematical model is a mathematical model that estimates the estimated time series on the basis of an input time series that is a time series indicating an input sound and second difference information that is information indicating at least a partial difference between the input time series and the estimated time series, and the estimation condition is a condition that a difference be

Abstract: The number of conversational tests required for evaluation of acoustic quality of the ICC system is reduced. An evaluation value converting device 3 evaluates the quality of a conversation made across a near-end acoustic area 100 and a far-end acoustic area 200 inside a vehicle in which a plurality of acoustic areas are predetermined. A voice signal collected by a microphone M2 disposed in the far-end acoustic area 200 is emitted from a speaker S1 disposed in the near-end acoustic area 100.

Abstract: A signal filtering device includes: an information generation unit that generates feature information on related information on a target signal; an extraction unit that extracts mask information from a mixed signal including the target signal on the basis of the feature information; and a mask processing unit that estimates the target signal from the mixed signal using the mask information. The information generation unit may encode the related information into a multidimensional vector and generate a linear transformation result of the multidimensional vector as the feature information. The information generation unit may encode the related information into a first multidimensional vector, encode the mixed signal into a second multidimensional vector, derive a similarity in time series between the first multidimensional vector and the second multidimensional vector, and generate a result of a weighted sum of the similarity in time series and the mixed signal as the feature information.

Abstract: A signal filtering device includes: a separation unit that separates a predetermined number of possibility signals from a mixed signal as possibilities of a target signal; an encoding unit that encodes related information of the target signal into a first feature vector and encodes the predetermined number of possibility signals into the predetermined number of second feature vectors; and a selection unit that derives a similarity between the first feature vector and the second feature vector for each of the possibility signals, and selects a possibility signal of the possibility signals having the highest similarity as the target signal from the predetermined number of possibility signals. The selection unit may derive an inner product of the first feature vector and the second feature vector as the similarity. The predetermined number of possibility signals may be voice signals associated with the predetermined number of sound sources.

Abstract: An anomaly detection technique which realizes high accuracy while reducing cost required for normal model learning is provided. An anomaly detection apparatus includes an anomaly degree estimating unit configured to estimate an anomaly degree indicating a degree of anomaly of anomaly detection target equipment from sound emitted from the anomaly detection target equipment (hereinafter, referred to as anomaly detection target sound) based on association between a first probability distribution indicating distribution of normal sound emitted from one or more pieces of equipment different from the anomaly detection target equipment and normal sound emitted from the anomaly detection target equipment (hereinafter, referred to as normal sound for adaptive learning).

Abstract: A possible region of encoding results of anomalous samples is limited. An encoder storage unit 14 stores an encoder for projecting an input feature value into a latent space in which the latent space is a closed manifold, a normal distribution obtained by learning normal data and an anomalous distribution obtained by learning anomalous data are held on the manifold, and a decoder for reconstructing the output of the encoder. An encoding unit 15 obtains a reconstruction result output by the decoder when a feature value of target data is input to the encoder. An anomaly score calculation unit 16 calculates an anomaly score of the target data based on distances between the reconstruction result and the normal distribution and distances between the reconstruction result and the anomalous distribution.

Abstract: A coding method and a decoding method are provided which can use in combination a predictive coding and decoding method which is a coding and decoding method that can accurately express coefficients which are convertible into linear prediction coefficients with a small code amount and a coding and decoding method that can obtain correctly, by decoding, coefficients which are convertible into linear prediction coefficients of the present frame if a linear prediction coefficient code of the present frame is correctly input to a decoding device.

Abstract: The number of conversational tests needed for the evaluation of acoustic quality of the ICC system is reduced. An evaluation value conversion device 3 evaluates the quality of communication between a near-end acoustic region 100 and a far-end acoustic region 200 inside a vehicle for which a plurality of acoustic regions are predetermined. A voice signal picked up by a microphone M2 disposed in the far-end acoustic region 200 is emitted from a speaker S1 disposed in the near-end acoustic region 100.

Abstract: A technique for stably optimizing a variable of model so as to conform the learning data set is provided, even when there is a statistical deviation in a learning data set distributed and accumulated in a plurality of nodes, or communication between nodes is asynchronous and sparse.

Abstract: One aspect of the present invention is a learning device including a self-learning unit that updates content of main conversion processing for converting data to be processed into data in a predetermined format by executing self-supervised learning, and a data augmentation unit that executes data augmentation processing of generating data to be processed in the main conversion processing based on an acoustic time series, in which the data augmentation unit performs acoustic time series clipping processing of clipping a partial time series that is a time series of a part of the acoustic time series, duplication processing of duplicating the partial time series, and conversion processing of converting one and the other of the partial time series according to a predetermined rule, and the self-learning unit updates the content of the main conversion processing by self-supervised learning based on a result obtained by the conversion processing.

Abstract: A technology of accurately coding and decoding coefficients which are convertible into linear prediction coefficients even for a frame in which the spectrum variation is great while suppressing an increase in the code amount as a whole is provided. A coding device includes: a first coding unit that obtains a first code by coding coefficients which are convertible into linear prediction coefficients of more than one order; and a second coding unit that obtains a second code by coding at least quantization errors of the first coding unit if (A?1) an index Q commensurate with how high the peak-to-valley height of a spectral envelope is, the spectral envelope corresponding to the coefficients which are convertible into the linear prediction coefficients of more than one order, is larger than or equal to a predetermined threshold value Th1 and/or (B?1) an index Q? commensurate with how short the peak-to-valley height of the spectral envelope is, is smaller than or equal to a predetermined threshold value Th1?.