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

TL;DR

This paper presents a multi-pass non-negative matrix factorization approach for DJ mix transcription, improving efficiency and accuracy in identifying source tracks and effects, with promising results compared to baseline methods.

Contribution

Introduces a multi-pass NMF algorithm with inter-pass filtering for DJ mix transcription, addressing computational costs and enhancing temporal continuity and sparseness.

Findings

Promising results compared to DTW baseline

Effective in identifying source tracks and effects

Potential for future NMF-based applications

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.