Automatic drum transcription with convolutional neural networks - Archive ouverte HAL
Communication Dans Un Congrès Année : 2018

Automatic drum transcription with convolutional neural networks

Céline Jacques
  • Fonction : Auteur
  • PersonId : 975532
Axel Roebel

Résumé

Automatic drum transcription (ADT) aims to detect drum events in polyphonic music. This task is part of the more general problem of transcribing a music signal in terms of its musical score and additionally can be very interesting for extracting high level information e.g. tempo, downbeat, measure. This article has the objective to investigate the use of Convolutional Neural Networks (CNN) in the context of ADT. Two different strategies are compared. First an approach based on a CNN based detection of drum only onsets is combined with an algorithm using Non-negative Matrix Decon-volution (NMD) for drum onset transcription. Then an approach relying entirely on CNN for the detection of individual drum instruments is described. The question of which loss function is the most adapted for this task is investigated together with the question of the optimal input structure. All algorithms are evaluated using the publicly available ENST Drum database, a widely used established reference dataset, allowing easy comparison with other algorithms. The comparison shows that the purely CNN based algorithm significantly outperforms the NMD based approach, and that the results are significantly better for the snare drum, but slightly worse for both the bass drum and the hi-hat when compared to the best results published so far and ones using also a neural network model.
Fichier principal
Vignette du fichier
DAFx2018_paper_59.pdf (618.25 Ko) Télécharger le fichier
Origine Fichiers éditeurs autorisés sur une archive ouverte
Loading...

Dates et versions

hal-02018777 , version 1 (14-02-2019)

Identifiants

  • HAL Id : hal-02018777 , version 1

Citer

Céline Jacques, Axel Roebel. Automatic drum transcription with convolutional neural networks. 21th International Conference on Digital Audio Effects, Sep 2018, Aveiro, Portugal, Sep 2018, Aveiro, Portugal. ⟨hal-02018777⟩
338 Consultations
1282 Téléchargements

Partager

More