Deep learning networks have been successfully applied to solve a large number of tasks. The effectiveness of deep learning networks is limited by the amount and the variety of data used for the training. For this reason, deep-learning networks can be applied in scenarios where a huge amount of data are available. In music information retrieval, this is the case of popular genres due to the wider availability of annotated music pieces. Instead, to find sufficient and useful data is a hard task for non widespread genres, like, for instance, traditional and folk music. To address this issue, Transfer Learning has been proposed, i.e., to train a network using a large available dataset and then transfer the learned knowledge (the hierarchical representation) to another task. In this work, we propose an approach to apply transfer learning for beat tracking. We use a deep BLSTM-based RNN as the starting network trained on popular music, and we transfer it to track beats of Greek folk music. In order to evaluate the effectiveness of our approach, we collect a dataset of Greek folk music, and we manually annotate the pieces.

Beat tracking using recurrent neural network: A transfer learning approach

Buccoli M.;Zanoni M.;Antonacci F.;Sarti A.
2018

Abstract

Deep learning networks have been successfully applied to solve a large number of tasks. The effectiveness of deep learning networks is limited by the amount and the variety of data used for the training. For this reason, deep-learning networks can be applied in scenarios where a huge amount of data are available. In music information retrieval, this is the case of popular genres due to the wider availability of annotated music pieces. Instead, to find sufficient and useful data is a hard task for non widespread genres, like, for instance, traditional and folk music. To address this issue, Transfer Learning has been proposed, i.e., to train a network using a large available dataset and then transfer the learned knowledge (the hierarchical representation) to another task. In this work, we propose an approach to apply transfer learning for beat tracking. We use a deep BLSTM-based RNN as the starting network trained on popular music, and we transfer it to track beats of Greek folk music. In order to evaluate the effectiveness of our approach, we collect a dataset of Greek folk music, and we manually annotate the pieces.
European Signal Processing Conference
978-9-0827-9701-5
File in questo prodotto:
File Dimensione Formato  
EUSIPCO2018 - Beat Tracking Using Recurrent Neural Network- a Transfer Learning Approach.pdf

Accesso riservato

: Publisher’s version
Dimensione 425.81 kB
Formato Adobe PDF
425.81 kB Adobe PDF   Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/11311/1158414
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 1
  • ???jsp.display-item.citation.isi??? 1
social impact