Investigation of Acoustic Features of God Names based on Grad-CAM Saliency Maps
Kaoru Shimizu, Tsuyoshi Nakamura · 2022 Joint 12th International Conference on Soft Computing and Intelligent Systems and 23rd International Symposium on Advanced Intelligent Systems (SCIS&ISIS) · 2022
The phenomenon in which a specific sound gives a specific image to a person is called sound symbolism. There have been many reports on sound symbolism in linguistics, psychology and other fields. However, the reports have not clarified all of sound symbolism. In order to clarify the whole of sound symbolism, we would like to collect examples suspected of having sound symbolism and investigate by bottom-up analysis by using them. Our study took up god names, which is considered to be an example of sound symbolism, and investigated the acoustic features of Japanese and foreign god names. We used Convolutional Neural Network (CNN) and Grad-CAM for the investigation, and analysed the features based on the classification results. As a result, we have found some acoustic features that can distinguish between Japanese and foreign god names.