Pré-Publication, Document De Travail Année : 2024

DJ Mix Transcription with Multi-Pass Non-Negative Matrix Factorization

Résumé

DJ mix transcription is a crucial step towards DJ mix reverse engineering, which estimates the set of parameters and audio effects applied to a set of existing tracks to produce a performative DJ mix. We introduce a new approach based on a multi-pass NMF algorithm where the dictionary matrix corresponds to a set of spectrogram slices of the source tracks present in the mix. The multi-pass strategy is motivated by the high computational cost resulting from the use of a large NMF dictionary. The proposed method uses inter-pass filtering to favor temporal continuity and sparseness and is evaluated on a publicly available dataset. Our comparative results considering a baseline method based on dynamic time warping (DTW) are promising and pave the way of future NMF-based applications.

Fichier principal
Vignette du fichier
2410.04198v1.pdf (617.75 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence
DOI

Fait partie de 10.5281/zenodo.1422384 Jeu de données Schwarz, D., & Fourer, D. (2018). UnmixDB: A Dataset for DJ-Mix Information Retrieval (Version 1) [Data set]. Zenodo. https://doi.org/10.5281/ZENODO.1422384

Dates et versions

hal-04995821 , version 1 (18-03-2025)

Licence

Identifiants

Citer

Étienne Paul André, Dominique Fourer, Diemo Schwarz. DJ Mix Transcription with Multi-Pass Non-Negative Matrix Factorization. 2024. ⟨hal-04995821⟩
219 Consultations
196 Téléchargements

Altmetric

Partager

  • More