Work

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

Year: 2024

Type: preprint

Abstract: 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.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.2410.04198

Authors: André, Étienne Paul, Fourer, Dominique, Schwarz, Diemo

Institutions: Institut de Recherche et Coordination Acoustique Musique, Informatique, BioInformatique, Systèmes Complexes, Université d'Évry Val-d'Essonne, Centre National de la Recherche Scientifique, Ministère de la Culture, Sciences et Technologies de la Musique et du Son

Language: English

Topic: Music and Audio Processing

Subfield: Signal Processing

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funder: Agence Nationale de la Recherche

Award: Audio Quality Analysis for Representing, Indexing and Unifying Signals

OpenAlex ID: W4403322532

Cites:

Cited by:

Related to: 10