Sound processing methods, training methods for estimation models, sound processing systems and recording media

Abstract

The audio processing system has an acquisition unit and a generation unit. The acquisition unit acquires input data, which includes: first sound data representing a first component of a first frequency band in a first sound corresponding to a first sound source; second sound data representing a second component of the first frequency band in a second sound corresponding to a second sound source different from the first sound source; and mixed sound data representing a component of a mixed sound of the first sound and the second sound that includes a second frequency band different from the first frequency band. The generation unit inputs the input data into a trained estimation model, thereby generating at least one of first output data and second output data, wherein the first output data represents a component of the first sound that includes the second frequency band, and the second output data represents a component of the second sound that includes the second frequency band.

Images