English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Music source separation performance has greatly improved in recent years withthe advent of approaches based on deep learning. Such methods typically requirelarge amounts of labelled training data, which in the case of music consist ofmixtures and corresponding instrument stems. However, stems are unavailable formost commercial music, and only limited datasets have so far been released tothe public. It can thus be difficult to draw conclusions when comparing varioussource separation methods, as the difference in performance may stem as muchfrom better data augmentation techniques or training tricks to alleviate thelimited availability of training data, as from intrinsically better modelarchitectures and objective functions. In this paper, we present thesynthesized Lakh dataset (Slakh) as a new tool for music source separationresearch. Slakh consists of high-quality renderings of instrumental mixturesand corresponding stems generated from the Lakh MIDI dataset (LMD) usingprofessional-grade sample-based virtual instruments. A first version,Slakh2100, focuses on 2100 songs, resulting in 145 hours of mixtures. While notfully comparable because it is purely instrumental, this dataset contains anorder of magnitude more data than MUSDB18, the {\it de facto} standard datasetin the field. We show that Slakh can be used to effectively augment existingdatasets for musical instrument separation, while opening the door to a widearray of data-intensive music signal analysis tasks.

Cutting Music Source Separation Some Slakh: A Dataset to Study the Impact of Training Data Quality and Quantity