Abstract: For example, learning data used for machine learning is efficiently generated. A learning data generating device configured to generate learning data used for learning of a machine learning model, the device including: a data acquisition unit that acquires input data; and a conversion unit that converts the input data into learning data by performing processing on the input data on the basis of a characteristic difference between a characteristic corresponding to a first condition and a characteristic corresponding to a second condition different from the first condition.

Abstract: Provided is a signal processing device that performs noise canceling by combining a feedforward method and a feedback method. A signal processing device includes: a correlation calculation unit that calculates a correlation between a first sound pickup signal by a first microphone installed outside a predetermined region and a second sound pickup signal by a second microphone installed in the predetermined region; a determination unit that determines the correlation; and a control unit that performs control based on a result of the determination. The control unit controls execution of signal processing for generating a cancellation signal to be output within the predetermined region from the first sound pickup signal and the second sound pickup signal or output of the cancellation signal.

Abstract: Provided is a learning method, a learning program, a learning device, and a learning system, for training a classification model, to further raise the correct answer rate of classification by the classification model. The learning method includes execution of generating one piece of composite data by compositing a plurality of pieces of training data of which classification has each been set, or a plurality of pieces of converted data obtained by converting the plurality of pieces of training data, at a predetermined ratio, inputting one or a plurality of pieces of the composite data into the classification model, and updating a parameter of the classification model so that classification of the plurality of pieces of training data included in the composite data is replicated at the predetermined ratio by output of the classification model, by a computer provided with at least one hardware processor and at least one memory.

Abstract: The present technology relates to a particular-sound detector and method, and a program that make it possible to improve the performance of detecting particular sounds. The particular-sound detector includes a particular-sound detecting section that detects a particular sound on a basis of a plurality of audio signals obtained by collecting sounds by a plurality of microphones provided to a wearable device. In addition, the plurality of the microphones includes two microphones that are equidistant at least from a sound source of the particular sound, and one microphone arranged at a predetermined position. The present technology can be applied to headphones.

Abstract: The present technology relates to a neural network device capable of improving recognition performance. The neural network device includes a non-linear transformation layer processing unit that performs a transformation with a non-linear function having a learnable parameter. The present technology can be applied to a neural network.

Abstract: Provided is a learning method, a learning program, a learning device, and a learning system, for training a classification model, to further raise the correct answer rate of classification by the classification model. The learning method includes execution of generating one piece of composite data by compositing a plurality of pieces of training data of which classification has each been set, or a plurality of pieces of converted data obtained by converting the plurality of pieces of training data, at a predetermined ratio, inputting one or a plurality of pieces of the composite data into the classification model, and updating a parameter of the classification model so that classification of the plurality of pieces of training data included in the composite data is replicated at the predetermined ratio by output of the classification model, by a computer provided with at least one hardware processor and at least one memory.