The 2018 Signal Separation Evaluation Campaign

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 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.

arXiv commentTo appear in International Conference on Latent Variable Analysis and Signal Separation

Cited by in corpus (8)

• Deep Filtering: Signal Extraction and Reconstruction Using Complex Time-Frequency Filters
• Music Demixing Challenge 2021
• Independent Vector Extraction for Fast Joint Blind Source Separation and Dereverberation
• Audio query-based music source separation
• Music Source Separation with Generative Flow
• Toward Deep Drum Source Separation
• In-Network Processing Acoustic Data for Anomaly Detection in Smart Factory
• Spectrogram-channels u-net: a source separation model viewing each channel as the spectrogram of each source