On the Human and Computer Alignment of Attribute-Based Music Matches
This work designs a triplet-based forced-choice task comprising 300 cases, including plagiarism examples, cover songs, and AI-generated music, and introduces the MATCHA dataset, a collection of 1105 perceptual assessments of attribute-based music matches from 83 expert participants.
Roser Batlle-Roca, Woo-Sung Choi, Joan Serrà et al.
· 0 citations