Communication Dans Un Congrès Année : 2020

Uncovering Audio Patterns in Music with Nonnegative Tucker Decomposition for Structural Segmentation

Résumé

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.

Fichier principal
Vignette du fichier
Uncovering audio patterns in music with Nonnegative Tucker Decomposition for structural segmentation.pdf (482.78 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence
Loading...
HAL

Référence hal-02915456 Logiciel Axel Marmoret, Jérémy E Cohen. nn_fac: Nonnegative Factorization techniques toolbox. 2020, ⟨swh:1:dir:ec2a2153951a7f79b7d980ea0d9c7601e5755de9;origin=https://hal.archives-ouvertes.fr/hal-02915456;visit=swh:1:snp:6e4be34b95db089bc5e4455abb4037d0b633b9fe;anchor=swh:1:rev:88782798ee67126597c52fb12312a462e9f6439b;path=/⟩. ⟨hal-02915456⟩

HAL

Fait partie de hal-03409508 Objet présenté à une conférence Axel Marmoret, Florian Voorwinden, Valentin Leplat, Jérémy E Cohen, Frédéric Bimbot. Nonnegative Tucker Decomposition with Beta-divergence for Music Structure Analysis of audio signals. GRETSI, XXVIIIème Colloque Francophone de Traitement du Signal et des Images, Sep 2022, Nancy, France. ⟨hal-03409508⟩

HAL

A comme partie hal-04323556 Article Axel Marmoret, Jérémy E Cohen, Frédéric Bimbot. Barwise Music Structure Analysis with the Correlation Block-Matching Segmentation Algorithm. Transactions of the International Society for Music Information Retrieval (TISMIR), 2023, 6 (1), pp.167-185. ⟨10.5334/tismir.167⟩. ⟨hal-04323556⟩

Dates et versions

hal-02928733 , version 1 (02-09-2020)

Licence

Identifiants

  • HAL Id : hal-02928733 , version 1

Citer

Axel Marmoret, Jérémy E Cohen, Nancy Bertin, Frédéric Bimbot. Uncovering Audio Patterns in Music with Nonnegative Tucker Decomposition for Structural Segmentation. ISMIR 2020 - 21st International Society for Music Information Retrieval, Oct 2020, Montréal (Online), Canada. pp.1-7. ⟨hal-02928733⟩
574 Consultations
548 Téléchargements

Partager

  • More