Understanding Human Perception of Music Plagiarism Through a Computational Approach
Daeun Hwang, Hyeonbin Hwang
TL;DR
The paper investigates how humans perceive music similarity and potential plagiarism by focusing on three structural features: melody, rhythm, and chord progression. It proposes data-driven criteria for plagiarism and introduces an LLM-as-a-judge framework that reasonedly combines high-level feature insights to predict perceived similarity. A controlled, synthetic-data study is outlined to link perceptual judgments with computational measures such as MFCC and chroma features, and to guide the development of a more robust plagiarism-detection model. If successful, this approach could bridge human perception and algorithmic similarity, informing future MIR tools and copyright-risk assessment.
Abstract
There is a wide variety of music similarity detection algorithms, while discussions about music plagiarism in the real world are often based on audience perceptions. Therefore, we aim to conduct a study to examine the key criteria of human perception of music plagiarism, focusing on the three commonly used musical features in similarity analysis: melody, rhythm, and chord progression. After identifying the key features and levels of variation humans use in perceiving musical similarity, we propose a LLM-as-a-judge framework that applies a systematic, step-by-step approach, drawing on modules that extract such high-level attributes.