Method for learning mapping

A method for learning a mapping used to identify a cause of a sound in a vehicle based on a sound signal that is a signal related to a sound received by a microphone, wherein the mapping is a learning model that outputs a variable indicating the cause of the sound in the vehicle when the sound signal is input to the mapping as an input variable, the method comprising:

• executing, with processing circuitry, a signal correction process that corrects the sound signal by superimposing a noise signal on the sound signal;
• and
• executing, with the processing circuitry, an update process that updates the mapping through machine learning in which the sound signal corrected in the signal correction process serves as training data and the cause of the sound paired with the sound signal serves as teaching data.