MULTI-STEP CHORD SEQUENCE PREDICTION BASED ON AGGREGATED MULTI-SCALE ENCODER-DECODER NETWORKS - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2019

MULTI-STEP CHORD SEQUENCE PREDICTION BASED ON AGGREGATED MULTI-SCALE ENCODER-DECODER NETWORKS

Andrew Mcleod
  • Fonction : Auteur
Philippe Esling
Jérôme Nika
Eita Nakamura
  • Fonction : Auteur
  • PersonId : 968804
Kazuyoshi Yoshii
  • Fonction : Auteur
  • PersonId : 1015486

Résumé

This paper studies the prediction of chord progressions for jazz music by relying on machine learning models. The motivation of our study comes from the recent success of neu-ral networks for performing automatic music composition. Although high accuracies are obtained in single-step prediction scenarios, most models fail to generate accurate multi-step chord predictions. In this paper, we postulate that this comes from the multi-scale structure of musical information and propose new architectures based on an iterative temporal aggregation of input labels. Specifically, the input and ground truth labels are merged into increasingly large temporal bags, on which we train a family of encoder-decoder networks for each temporal scale. In a second step, we use these pre-trained encoder bottleneck features at each scale in order to train a final encoder-decoder network. Furthermore, we rely on different reductions of the initial chord alphabet into three adapted chord alphabets. We perform evaluations against several state-of-the-art models and show that our multi-scale architecture outperforms existing methods in terms of accuracy and perplexity, while requiring relatively few parameters. We analyze musical properties of the results, showing the influence of downbeat position within the analysis window on accuracy , and evaluate errors using a musically-informed distance metric.
Fichier principal
Vignette du fichier
Carsault_MLSP_2019.pdf (1.06 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-02364054 , version 1 (14-11-2019)

Identifiants

  • HAL Id : hal-02364054 , version 1

Citer

Tristan Carsault, Andrew Mcleod, Philippe Esling, Jérôme Nika, Eita Nakamura, et al.. MULTI-STEP CHORD SEQUENCE PREDICTION BASED ON AGGREGATED MULTI-SCALE ENCODER-DECODER NETWORKS. MLSP 2019, Oct 2019, Pittsburgh, United States. ⟨hal-02364054⟩
83 Consultations
162 Téléchargements

Partager

Gmail Facebook X LinkedIn More