A method and a system for instrument separating and reproducing for a mixture audio source is provided. The method and/or the system includes inputting selected music into an instrument separation model for extracting features therefrom, determining audio source signals of multiple channels for the separation of all instruments, each channel containing sound of one instrument, and transmitting the signals of the different channels to multiple speakers placed at designated positions for playing, which can reproduce or recreate an immersive sound field listening experience for users.

An information processing device 11 including: a control data generation unit that inputs analysis data X that is to be processed, to a trained model that has learnt a relationship between analysis data X that represents a time series of musical notes, and control data Y for controlling movements of an object that represents a performer, thereby generating control data Y according to the analysis data X.

The present disclosure relates to an information processing apparatus, an information processing method, and a program that make it possible to adjust commonness and eccentricity of automatically generated content by likelihood exploration while satisfying reality.

Input content including a sequence of data is encoded to be converted into a latent variable, the latent variable is decoded to reconfigure output content, a loss function is calculated on the basis of a likelihood of the input content which is an input sequence, a gradient of the loss function is lowered to update the latent variable, and the updated latent variable is decoded to reconfigure output content. The present invention can be applied to an automatic content generation device.

A parameter inference method realized by a computer, includes obtaining target performance information indicating a performance of music using an electronic musical instrument; inferring assist information from the target performance information with use of a trained inference model generated through machine learning, the assist information being related to setting of a parameter of the electronic musical instrument that conforms to a tendency of the performance; and outputting the inferred assist information related to the setting of the parameter.

An information processing method according to the present invention includes providing first musical piece information representing contents of a musical piece and performance information relating to a past performance prior to one unit period within the musical piece to a learner that has undergone learning relating to a specific tendency that relates to a performance, and generating, for the one unit period, performance information that is based on the specific tendency with the learner.

A machine learning method for training a learning model includes: transforming a first audio type of audio data into a first image type of image data, wherein a first audio component and a second audio component are mixed in the first audio type of audio data, and the first image type of image data corresponds to the first audio type of audio data; transforming a second audio type of audio data into a second image type of image data, wherein the second audio type of audio data includes the first audio component without mixture of the second audio component, and the second image type of image data corresponds to the second audio type of audio data; and performing machine learning on the learning model with training data including sets of the first image type of image data and the second image type of image data.

A system, method and computer product for training a neural network system. The method comprises inputting an audio signal to the system to generate plural outputs f(X, Θ). The audio signal includes one or more of vocal content and/or musical instrument content, and each output f(X, Θ) corresponds to a respective one of the different content types. The method also comprises comparing individual outputs f(X, Θ) of the neural network system to corresponding target signals. For each compared output f(X, Θ), at least one parameter of the system is adjusted to reduce a result of the comparing performed for the output f(X, Θ), to train the system to estimate the different content types. In one example embodiment, the system comprises a U-Net architecture. After training, the system can estimate various different types of vocal and/or instrument components of an audio signal, depending on which type of component(s) the system is trained to estimate.

Methods, systems and computer program products are provided for determining acoustic feature vectors of query and target items in a first vector space, and mapping the acoustic feature vectors to a second vector space having a lower dimension. The distribution of vectors in the second vector space can then be used to identify items from the same songs, and/or items that are complementary. A mapping function is trained using a machine learning algorithm, such that complementary audio items are closer in the second vector space than the first, according to a given distance metric.

The present disclosure describes techniques for identifying music attributes. The described techniques comprises receiving audio data of a piece of music; determining at least one attribute of the piece of music based on the audio data of the piece of music using a model; the model comprising a convolutional neural network and a transformer; the model being pre-trained using training data, wherein the training data comprise labelled data associated with a first plurality of music samples and unlabelled data associated with a second plurality of music samples, the labelled data comprise audio data of the first plurality of music samples and label information indicative of attributes of the first plurality of music samples, and the unlabelled data comprise audio data of the second plurality of music samples.

A method for generating a musical composition based on user input is described. A first set of musical characteristics from a first input musical piece is received as an input vector. The first set of musical characteristics is perturbed to create a perturbed input vector as input in a first set of nodes in a first visible layer of an unsupervised neural net. The unsupervised neural net comprised of a plurality of computing layers, each computing layer composed of a respective set of nodes. The unsupervised neural net is operated to calculate an output vector from a higher level hidden layer in the unsupervised neural net. The output vector is used to create an output musical piece.