Perceptual vs. automated judgments of music copyright infringement

Music copyright lawsuits often result in multimillion dollar damage awards or settlements, yet there are few objective guidelines for applying copyright law in infringement claims involving musical works. Recent re-search has attempted to develop objective methods based on automated similarity algorithms, but there remains almost no data on the role of perceived similarity in mu-sic copyright decisions despite its crucial role in copy-right law. We collected perceptual data from 20 participants for 17 adjudicated copyright cases from the USA and Japan after editing the disputed sections to contain either full audio, melody only, or lyrics only. Due to the historical emphasis in legal opinions on melody as the key criterion for deciding infringement, we predicted that listening to melody-only versions would result in perceptual judgements that more closely matched actual past legal decisions. Surprisingly, however, we found no significant differences between the three conditions, with participants matching past decisions in between 50-60% of cases in all three conditions. Automated algorithms designed to calculate melodic and audio similarity produced comparable results: both algorithms were able to match past decisions with identical accuracy of 71% (12/17 cases). Analysis of cases that were difficult to classify suggests that melody, lyrics, and other factors sometimes interact in complex ways difficult to capture using quantitative metrics. We propose directions for further investigation of the role of similarity in music copy-right law using larger and more diverse samples of cases and enhanced methods, and adapting our perceptual experiment method to avoid relying for ground truth data only on court decisions (which may be subject to selection bias). Our results contribute to important practical debates, such as whether jury members should be allowed to listen to full audio recordings during copyright cases.