The 2018 Signal Separation Evaluation Campaign
It provides resources and benchmarks for the audio signal separation community, but is incremental as it builds on previous campaigns.
The paper organized the 2018 Signal Separation Evaluation Campaign (SiSEC 2018), focusing on audio separation by creating the MUSDB18 database with nearly 10 hours of audio and releasing open-source tools for evaluation, and reported participant results.
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 10h 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 BSSEval 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.