Deep neural network based multichannel audio source separation - Archive ouverte HAL Access content directly
Book Sections Year : 2018

Deep neural network based multichannel audio source separation

(1) , (2) , (1)
1
2

Abstract

This chapter presents a multichannel audio source separation framework where deep neural networks (DNNs) are used to model the source spectra and combined with the classical multichannel Gaussian model to exploit the spatial information. The parameters are estimated in an iterative expectation-maximization (EM) fashion and used to derive a multichannel Wiener filter. Different design choices and their impact on the performance are discussed. They include the cost functions for DNN training, the number of parameter updates, the use of multiple DNNs, and the use of weighted parameter updates. Finally, we present its application to a speech enhancement task and a music separation task. The experimental results show the benefit of the multichannel DNN-based approach over a single-channel DNN-based approach and the multichannel nonnegative matrix factorization based iterative EM framework.
Fichier principal
Vignette du fichier
nugraha_book18.pdf (760.62 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01633858 , version 1 (13-11-2017)

Identifiers

Cite

Aditya Arie Nugraha, Antoine Liutkus, Emmanuel Vincent. Deep neural network based multichannel audio source separation. Audio Source Separation, Springer, pp.157-195, 2018, 978-3-319-73030-1. ⟨10.1007/978-3-319-73031-8_7⟩. ⟨hal-01633858⟩
519 View
1458 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More