Perceptual musical similarity metric learning with graph neural networks - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Perceptual musical similarity metric learning with graph neural networks

Cyrus Vahidi
  • Fonction : Auteur
  • PersonId : 1259680
Emmanouil Benetos
Huy Phan
  • Fonction : Auteur
Dan Stowell
  • Fonction : Auteur
  • PersonId : 964488
György Fazekas
  • Fonction : Auteur
  • PersonId : 1191291

Résumé

Sound retrieval for assisted music composition depends on evaluating similarity between musical instrument sounds, which is partly influenced by playing techniques. Previous methods utilizing Euclidean nearest neighbours over acoustic features show some limitations in retrieving sounds sharing equivalent timbral properties, but potentially generated using a different instrument, playing technique, pitch or dynamic. In this paper, we present a metric learning system designed to approximate human similarity judgments between extended musical playing techniques using graph neural networks. Such structure is a natural candidate for solving similarity retrieval tasks, yet have seen little application in modelling perceptual music similarity. We optimize a Graph Convolutional Network (GCN) over acoustic features via a proxy metric learning loss to learn embeddings that reflect perceptual similarities. Specifically, we construct the graph's adjacency matrix from the acoustic data manifold with an example-wise adaptive k-nearest neighbourhood graph: Adaptive Neighbourhood Graph Neural Network (AN-GNN). Our approach achieves 96.4% retrieval accuracy compared to 38.5% with a Euclidean metric and 86.0% with a multilayer perceptron (MLP), while effectively considering retrievals from distinct playing techniques to the query example.
Fichier principal
Vignette du fichier
WASPAA_2023__Perceptual_Musical_Similarity_Metric_Learning_with_Graph_Neural_Networks.pdf (2.63 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04178191 , version 1 (07-08-2023)

Identifiants

  • HAL Id : hal-04178191 , version 1

Citer

Cyrus Vahidi, Shubhr Singh, Emmanouil Benetos, Huy Phan, Dan Stowell, et al.. Perceptual musical similarity metric learning with graph neural networks. IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA 2023), Oct 2023, New Paltz, NY, United States. ⟨hal-04178191⟩
110 Consultations
139 Téléchargements

Partager

Gmail Facebook X LinkedIn More