AutoMashup: Automatic Music Mashups Creation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Delabaere, Marine, Miqueu, Léa, Moreno, Michael, Bigois, Gautier, Duong, Hoang, Fernandez, Ella, Manent, Flavie, Salgado-Herrera, Maria, Pasdeloup, Bastien, Farrugia, Nicolas, Marmoret, Axel
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908484260331520
author Delabaere, Marine
Miqueu, Léa
Moreno, Michael
Bigois, Gautier
Duong, Hoang
Fernandez, Ella
Manent, Flavie
Salgado-Herrera, Maria
Pasdeloup, Bastien
Farrugia, Nicolas
Marmoret, Axel
author_facet Delabaere, Marine
Miqueu, Léa
Moreno, Michael
Bigois, Gautier
Duong, Hoang
Fernandez, Ella
Manent, Flavie
Salgado-Herrera, Maria
Pasdeloup, Bastien
Farrugia, Nicolas
Marmoret, Axel
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2508_06516
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle AutoMashup: Automatic Music Mashups Creation
Delabaere, Marine
Miqueu, Léa
Moreno, Michael
Bigois, Gautier
Duong, Hoang
Fernandez, Ella
Manent, Flavie
Salgado-Herrera, Maria
Pasdeloup, Bastien
Farrugia, Nicolas
Marmoret, Axel
Sound
Audio and Speech Processing
Signal Processing
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.
title AutoMashup: Automatic Music Mashups Creation
topic Sound
Audio and Speech Processing
Signal Processing
url https://arxiv.org/abs/2508.06516