Abstract
In this study, we construct an impression evaluation model for button sounds generated when users press the buttons on car audio equipment using a neural network. The dynamic characteristics of 11 kinds of button sounds obtained by their wavelet transform frequencies and sound pressure values are fed into the network model inputs. The model responds with three factor scores, "esthetic", "force" and "metallic", and an evaluation value of "offensive - pleasant" as the outputs. By analyzing the synaptic weights of the neurons on the neural network after training, we confirmed the model acquired a mechanism that extracted four impression evaluation values from the sound characteristics. This result shows that the model is able to attain automation of button sound design.
