Signal extraction system, signal extraction learning method, and signal extraction learning program

A signal extraction learning method comprising:

• inputting a neural network in which a first network having a layer for inputting an anchor signal belonging to a predetermined class and a mixed signal including a target signal belonging to the class and a layer for outputting, as an estimation result, a reconstruction mask indicating a time-frequency domain in which the target signal is present in the mixed signal and a second network having a layer for inputting the target signal extracted by applying the mixed signal to the reconstruction mask and a layer for outputting a result obtained by classifying the input target signal into a predetermined class are combined;
• applying an anchor signal and the mixed signal to the first network to estimate a reconstruction mask of a class to which the anchor signal belongs;
• applying the mixed signal to the estimated reconstruction mask to extract a target signal, and applying the extracted target signal to the second network to classify the target signal into a class;
• calculating a loss function between the class to which the extracted target signal is classified and a true class;
• updating a parameter of the first network and a parameter of the second network in the neural network based on the calculation result of the loss function;
• and
• outputting the updated first network.

A non-transitory computer readable information recording medium storing a signal extraction learning program, when executed by a processor, that performs a method for:

• inputting a neural network in which a first network having a layer for inputting an anchor signal belonging to a predetermined class and a mixed signal including a target signal belonging to the class and a layer for outputting, as an estimation result, a reconstruction mask indicating a time-frequency domain in which the target signal is present in the mixed signal and a second network having a layer for inputting the target signal extracted by applying the mixed signal to the reconstruction mask and a layer for outputting a result obtained by classifying the input target signal into a predetermined class are combined;
• applying an anchor signal and the mixed signal to the first network to estimate a reconstruction mask of a class to which the anchor signal belongs;
• applying the mixed signal to the estimated reconstruction mask to extract a target signal, and applying the extracted target signal to the second network to classify the target signal into a class;
• calculating a loss function between the class to which the extracted target signal is classified and a true class;
• updating a parameter of the first network and a parameter of the second network in the neural network based on the calculation result of the loss function;
• and
• outputting the updated first network.