AutoMashup: Automatic Music Mashups Creation

Marine Delabaere, Léa Miqueu, Michael Moreno, Gautier Bigois, Hoang Duong, Ella Fernandez, Flavie Manent, Maria Salgado-Herrera, Bastien Pasdeloup, Nicolas Farrugia, Axel Marmoret

Abstract: We introduce AutoMashup, a system for automatic mashup creation based on source separation, music analysis, and compatibility estimation. We propose using COCOLA to assess compatibility between separated stems and investigate whether general-purpose pretrained audio models (CLAP and MERT) can support zero-shot estimation of track pair compatibility. Our results show that mashup compatibility is asymmetric -- it depends on the role assigned to each track (vocals or accompaniment) -- and that current embeddings fail to reproduce the perceptual coherence measured by COCOLA. These findings underline the limitations of general-purpose audio representations for compatibility estimation in mashup creation.

External IDs:dblp:journals/corr/abs-2508-06516