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 Plus annual

Presents the access of premium content as premium feature

Premium Content

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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Music source separation is focused on extracting distinct sonic elements fromcomposite tracks. Historically, many methods have been grounded in supervisedlearning, necessitating labeled data, which is occasionally constrained in itsdiversity. More recent methods have delved into N-shot techniques that utilizeone or more audio samples to aid in the separation. However, a challenge withsome of these methods is the necessity for an audio query during inference,making them less suited for genres with varied timbres and effects. This paperoffers a proof-of-concept for a self-supervised music source separation systemthat eliminates the need for audio queries at inference time. In the trainingphase, while it adopts a query-based approach, we introduce a modification bysubstituting the continuous embedding of query audios with Vector Quantized(VQ) representations. Trained end-to-end with up to N classes as determined bythe VQ's codebook size, the model seeks to effectively categorise instrumentclasses. During inference, the input is partitioned into N sources, with somepotentially left unutilized based on the mix's instrument makeup. Thismethodology suggests an alternative avenue for considering source separationacross diverse music genres. We provide examples and additional results online.

Self-Supervised Music Source Separation Using Vector-Quantized Source Category Estimates