A Comprehensive Survey for Evaluation Methodologies of AI-Generated Music
It addresses the challenge of resource-intensive and less reproducible evaluation methods for researchers and practitioners in AI-generated music, but it is incremental as it surveys existing approaches rather than introducing new ones.
This study tackled the problem of evaluating AI-generated music by comprehensively assessing subjective, objective, and combined methodologies, highlighting their advantages and disadvantages to provide a reference for unifying evaluation in this field.
In recent years, AI-generated music has made significant progress, with several models performing well in multimodal and complex musical genres and scenes. While objective metrics can be used to evaluate generative music, they often lack interpretability for musical evaluation. Therefore, researchers often resort to subjective user studies to assess the quality of the generated works, which can be resource-intensive and less reproducible than objective metrics. This study aims to comprehensively evaluate the subjective, objective, and combined methodologies for assessing AI-generated music, highlighting the advantages and disadvantages of each approach. Ultimately, this study provides a valuable reference for unifying generative AI in the field of music evaluation.