Search papers, labs, and topics across Lattice.
This study introduces a five-dimensional diagnostic evaluation framework for assessing AI-generated cover songs, focusing on melodic pitch, harmonic progression, key consistency, style consistency, and arrangement quality. The analysis of 30 covers from six systems reveals that harmonic progression and arrangement errors are prevalent, with severe-error rates of 53% and 47%, respectively, while key consistency is generally maintained. Notably, the findings indicate that while low-level features can highlight specific issues, they cannot substitute for nuanced musical judgment in evaluating overall quality.
AI-generated covers often hide severe harmonic errors behind acceptable key consistency, challenging the reliability of global quality scores.
AI-generated covers often fail through local musical errors that a global quality score cannot locate: the vocal contour may remain recognizable while the accompaniment uses the wrong harmonic function, or the output may stay in key while the arrangement remains incomplete. We present a five-dimensional diagnostic framework covering melodic pitch, harmonic progression, key consistency, style consistency, and arrangement/production quality. The benchmark contains 30 covers generated from 5 source songs by 6 systems, with expert severity ratings and 9 symbolic or acoustic features. Harmonic progression and arrangement had the highest severe-error rates (53% and 47%), whereas key consistency was better preserved. Six covers combined acceptable key consistency with severe harmonic errors. Large-leap ratio had a nominal association with melodic ratings (Spearman rho = -0.429, uncorrected p = 0.018), but no feature correlation survived the nine-test multiplicity reference. An interpretable percentile-rule pilot likewise failed to outperform a fixed majority baseline reliably across 16 dimension-level comparisons. The results separate useful diagnostic evidence from dependable automatic scoring: low-level and symbolic summaries can expose particular symptoms, but they do not replace context-aware musical judgment.
