Research on AI Composition Recognition Based on Music Rules
This addresses copyright disputes in AI-generated music, though it appears incremental as it builds on existing music analysis techniques.
The paper tackles the problem of distinguishing AI-generated music from human compositions by developing a music-rule-identifying algorithm that analyzes mode stability, achieving successful distinction between datasets with different source distributions.
The development of artificial intelligent composition has resulted in the increasing popularity of machine-generated pieces, with frequent copyright disputes consequently emerging. There is an insufficient amount of research on the judgement of artificial and machine-generated works; the creation of a method to identify and distinguish these works is of particular importance. Starting from the essence of the music, the article constructs a music-rule-identifying algorithm through extracting modes, which will identify the stability of the mode of machine-generated music, to judge whether it is artificial intelligent. The evaluation datasets used are provided by the Conference on Sound and Music Technology(CSMT). Experimental results demonstrate the algorithm to have a successful distinguishing ability between datasets with different source distributions. The algorithm will also provide some technological reference to the benign development of the music copyright and artificial intelligent music.