The 2018 Signal Separation Evaluation Campaign - Archive ouverte HAL Access content directly
Conference Papers Year : 2018

The 2018 Signal Separation Evaluation Campaign

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

Abstract

This paper reports the organization and results for the 2018 community-based Signal Separation Evaluation Campaign (SiSEC 2018). This year's edition was focused on audio and pursued the effort towards scaling up and making it easier to prototype audio separation software in an era of machine-learning based systems. For this purpose, we prepared a new music separation database: MUSDB18, featuring close to 10 h of audio. Additionally, open-source software was released to automatically load, process and report performance on MUSDB18. Furthermore, a new official Python version for the BSS Eval toolbox was released, along with reference implementations for three oracle separation methods: ideal binary mask, ideal ratio mask, and multichannel Wiener filter. We finally report the results obtained by the participants.
Fichier principal
Vignette du fichier
SiSEC2018report.pdf (850.84 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

lirmm-01766791 , version 1 (14-04-2018)
lirmm-01766791 , version 2 (19-04-2018)

Identifiers

Cite

Fabian-Robert Stöter, Antoine Liutkus, Nobutaka Ito. The 2018 Signal Separation Evaluation Campaign. LVA/ICA: Latent Variable Analysis and Signal Separation, Jul 2018, Surrey, United Kingdom. pp.293-305, ⟨10.1007/978-3-319-93764-9_28⟩. ⟨lirmm-01766791v2⟩
521 View
1946 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More