Emotion-based AI Music Generation System with CVAE-GAN
Chih-Fang Huang, Chengyuan Huang
Abstract
Music emotion is important for listeners' cognition. With the rapid development of technology, the variety of music has become more diverse and spread faster. However, the cost of music production is still very high. To solve the problem, the AI music composition has gradually gained attention in recent years. The purpose of this study is to establish an automated composition system that includes music, emotions, and machine learning. The system includes the music database with emotional tags as input, and deep learning trains the CVAE-GAN model as the framework to produce the music segments corresponding to the specified emotions. The subjects listen to the results of the system and judge that music corresponds to the original emotion.