Poster Statement

Keywords: artificial intelligence, algorithmic composition, ethnic music, machine learning

Abstract

This paper describes the project, A.I. Ch’angga , that aims to simulate the music of the early 20th century’s Korea using machine learning. Ch’angga refers to the music that was educated in the schools in Korea mostly during Japanese Colonial Era in the early 20th century. This project has been initiated from the question: “What music would have been created in Korea in the early 20th century if there had not been Japanese colonial era?”. We built a music generation model using a LSTM network using music around the time from China, Russia, Japan, and Korea and had it generate music changing the degree of the influence from each country. Our preliminary results suggest that machine learning could be used to simulate the cultural products of an era based on a hypothetical history.

• Sang Hyeob Lee & Jusub Kim, Department of Art & Technology, Sogang University Seoul, Korea

Full text (PDF) p. 654-655

This research was supported by the MIST(Ministry of Science ICT), Korea, under the National Program for Excellence in SW)(2015-0-00910) supervised by the IITP (Institute for Information & Communications Technology Planning & Evaluation).