Multichannel Music Separation with Deep Neural Networks

Aditya Arie Nugraha 1 Antoine Liutkus 1 Emmanuel Vincent 1
1 MULTISPEECH - Speech Modeling for Facilitating Oral-Based Communication
Inria Nancy - Grand Est, LORIA - NLPKD - Department of Natural Language Processing & Knowledge Discovery
Abstract : This article addresses the problem of multichannel music separation. We propose a framework where the source spectra are estimated using deep neural networks and combined with spatial covariance matrices to encode the source spatial characteristics. The parameters are estimated in an iterative expectation-maximization fashion and used to derive a multichannel Wiener filter. We evaluate the proposed framework for the task of music separation on a large dataset. Experimental results show that the method we describe performs consistently well in separating singing voice and other instruments from realistic musical mixtures.
Document type :
Conference papers
Liste complète des métadonnées

Cited literature [33 references]  Display  Hide  Download

https://hal.inria.fr/hal-01334614
Contributor : Aditya Arie Nugraha <>
Submitted on : Wednesday, June 14, 2017 - 12:38:58 PM
Last modification on : Wednesday, April 3, 2019 - 1:22:55 AM
Document(s) archivé(s) le : Tuesday, December 12, 2017 - 4:09:53 PM

File

eusipco_w_ack.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01334614, version 2

Citation

Aditya Arie Nugraha, Antoine Liutkus, Emmanuel Vincent. Multichannel Music Separation with Deep Neural Networks. European Signal Processing Conference (EUSIPCO), Aug 2016, Budapest, Hungary. pp.1748-1752. ⟨hal-01334614v2⟩

Share

Metrics

Record views

338

Files downloads

509