{"ID":2888710,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.06516","arxiv_id":"2508.06516","title":"AutoMashup: Automatic Music Mashups Creation","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.","short_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 estimati...","url_abs":"https://arxiv.org/abs/2508.06516","url_pdf":"https://arxiv.org/pdf/2508.06516v1","authors":"[\"Marine Delabaere\",\"Léa Miqueu\",\"Michael Moreno\",\"Gautier Bigois\",\"Hoang Duong\",\"Ella Fernandez\",\"Flavie Manent\",\"Maria Salgado-Herrera\",\"Bastien Pasdeloup\",\"Nicolas Farrugia\",\"Axel Marmoret\"]","published":"2025-07-30T08:36:08Z","proceeding":"cs.SD","tasks":"[\"cs.SD\",\"eess.AS\",\"eess.SP\"]","methods":"[]","has_code":false}