# Uncovering audio patterns in music with Nonnegative Tucker Decomposition for structural segmentation

arXiv: https://arxiv.org/abs/2104.08580 · HTML: https://mlsanity.com/paper/2104.08580/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 23 references that are in the map.
- First posted on arXiv 17 Apr 2021.

## Builds on (most cited first, 3 of 3)

- [TensorLy: Tensor Learning in Python](https://mlsanity.com/paper/1610.09555/) (2016)
- [madmom: a new Python Audio and Music Signal Processing Library](https://mlsanity.com/paper/1605.07008/) (2016)
- [Efficient Nonnegative Tucker Decompositions: Algorithms and Uniqueness](https://mlsanity.com/paper/1404.4412/) (2014)

## Built on by (most cited first, 8 of 8)

- [Pitchclass2vec: Symbolic Music Structure Segmentation with Chord Embeddings](https://mlsanity.com/paper/2303.15306/) (2023)
- [Efficient Algorithms for Regularized Nonnegative Scale-invariant Low-rank Approximation Models](https://mlsanity.com/paper/2403.18517/) (2024)
- [Identifiability of Nonnegative Tucker Decompositions -- Part I: Theory](https://mlsanity.com/paper/2505.12713/) (2025)
- [Nonnegative Tucker Decomposition with Beta-divergence for Music Structure Analysis of Audio Signals](https://mlsanity.com/paper/2110.14434/) (2021)
- [Exploring single-song autoencoding schemes for audio-based music structure analysis](https://mlsanity.com/paper/2110.14437/) (2021)
- [Dictionary-based Low-Rank Approximations and the Mixed Sparse Coding problem](https://mlsanity.com/paper/2111.12399/) (2021)
- [Barwise Compression Schemes for Audio-Based Music Structure Analysis](https://mlsanity.com/paper/2202.04981/) (2022)
- [TimeCues Studio: A Workspace for Music Annotation and Algorithm Prototyping](https://mlsanity.com/paper/2609.10338/) (2026)

## Abstract (arXiv)

Recent work has proposed the use of tensor decomposition to model repetitions and to separate tracks in loop-based electronic music. The present work investigates further on the ability of Nonnegative Tucker Decompositon (NTD) to uncover musical patterns and structure in pop songs in their audio form. Exploiting the fact that NTD tends to express the content of bars as linear combinations of a few patterns, we illustrate the ability of the decomposition to capture and single out repeated motifs in the corresponding compressed space, which can be interpreted from a musical viewpoint. The resulting features also turn out to be efficient for structural segmentation, leading to experimental results on the RWC Pop data set which are potentially challenging state-of-the-art approaches that rely on extensive example-based learning schemes.