English

AutoMashup: Automatic Music Mashups Creation

Sound 2025-08-12 v1 Audio and Speech Processing Signal Processing

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.

Cite

@article{arxiv.2508.06516,
  title  = {AutoMashup: Automatic Music Mashups Creation},
  author = {Marine Delabaere and Léa Miqueu and Michael Moreno and Gautier Bigois and Hoang Duong and Ella Fernandez and Flavie Manent and Maria Salgado-Herrera and Bastien Pasdeloup and Nicolas Farrugia and Axel Marmoret},
  journal= {arXiv preprint arXiv:2508.06516},
  year   = {2025}
}
R2 v1 2026-07-01T04:41:31.843Z