Looking at the world, we see that diversity, including a wide variety of languages, religions, and lifestyles, has supported the survival of humankind. Among these, song and dance have enriched people’s lives. Song and dance have elements that allow them to be smoothly accepted by people in countries without a common language. For example, K-POP possesses elements that can be enjoyed by people in Asia and the West who do not share a common language. When K-POP groups perform in Japan, young Japanese people readily accept them. This phenomenon is not limited to Japan; it is also seen in the United States and Europe. According to cultural anthropologists, there seem to be patterns that are easily accepted across national borders. According to cultural anthropologists’ analysis, myths and stories from around the world can be classified into about 30 patterns. These 30 patterns of music and body language express true joy and sorrow.
The benefits of song are also beginning to be understood from the songs of small birds. In the world of wild birds, females accept the advances of males with good songs. The spring calls of small birds become their fight for survival. It was already known that the attractive courtship calls of male birds attract females. Recently, it has been discovered that these attractive courtship calls tend to be pleasing to humans as well. A research team from Yale University in the US and McGill University in Canada investigated these courtship calls and human preferences for them. They investigated what kind of preferences humans have for the calls of various animals. As a result of this research, they discovered that there are commonalities in the sound preferences of humans and animals. This has led to the hypothesis that aesthetic sensibilities such as tone and rhythm are inherent in both humans and animals.
Even after humans left Africa and migrated to various regions and settled in those areas, what brings joy and sorrow is often similar across countries. Joy and sorrow were expressed not through spoken words, but through song (rhythm, melody, harmony) and body language. It can be said that this song and body language were the true expressions of joy and sorrow. Current image generation AIs generate images when instructed in text form, specifying the desired picture or image. The instructions humans input to obtain output from the generation AI are called prompts. Of course, prompts will be possible not only for images but also for music. Analyzing myths and stories from around the world, we were able to classify them into about 30 patterns. Among these are stories and tales that feel pleasant to hear, read, or see. We found that these pleasant stories share a common “pattern.” There are also pleasant and good songs. It might be interesting to train an AI to learn the “patterns” of pleasant songs and use them to create music that enriches the hearts of individuals.
