In this paper, we propose a deep recurrent neural network (DRNN), based on the Long Short-Term Memory (LSTM) unit, for the separation of drum and bass sources from a monaural audio track. In particular, a single DRNN with a total of six hidden layers (three feedforward and three recurrent) is used for each original source to be separated. In this work, we limit our attention to the case of only two, challenging sources: drum and bass. Some experimental results show the effectiveness of the proposed approach with respect to another state-of-the-art method. Results are expressed in terms of well-known metrics in the field of source separation.

Separation of drum and bass from monaural tracks / Scarpiniti, Michele; Scardapane, Simone; Comminiello, Danilo; Parisi, Raffaele; Uncini, Aurelio. - (2019), pp. 141-151. - SMART INNOVATION, SYSTEMS AND TECHNOLOGIES. [10.1007/978-3-319-95098-3_13].

Separation of drum and bass from monaural tracks

Scarpiniti, Michele
;
Scardapane, Simone;Comminiello, Danilo;Parisi, Raffaele;Uncini, Aurelio
2019

Abstract

In this paper, we propose a deep recurrent neural network (DRNN), based on the Long Short-Term Memory (LSTM) unit, for the separation of drum and bass sources from a monaural audio track. In particular, a single DRNN with a total of six hidden layers (three feedforward and three recurrent) is used for each original source to be separated. In this work, we limit our attention to the case of only two, challenging sources: drum and bass. Some experimental results show the effectiveness of the proposed approach with respect to another state-of-the-art method. Results are expressed in terms of well-known metrics in the field of source separation.
978-3-319-95097-6
978-3-319-95098-3
File allegati a questo prodotto
File Dimensione Formato  
Scarpiniti_Separation-of-drum_2019.pdf

solo gestori archivio

Tipologia: Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 645.04 kB
Formato Adobe PDF
645.04 kB Adobe PDF   Visualizza/Apri   Richiedi una copia

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/11573/1241924
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? ND
social impact