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 (MSS) faces challenges due to the limitedavailability of correctly-labeled individual instrument tracks. With the pushto acquire larger datasets to improve MSS performance, the inevitability ofencountering mislabeled individual instrument tracks becomes a significantchallenge to address. This paper introduces an automated technique for refiningthe labels in a partially mislabeled dataset. Our proposed self-refiningtechnique, employed with a noisy-labeled dataset, results in only a 1% accuracydegradation in multi-label instrument recognition compared to a classifiertrained on a clean-labeled dataset. The study demonstrates the importance ofrefining noisy-labeled data in MSS model training and shows that utilizing therefined dataset leads to comparable results derived from a clean-labeleddataset. Notably, upon only access to a noisy dataset, MSS models trained on aself-refined dataset even outperform those trained on a dataset refined with aclassifier trained on clean labels.

Self-refining of Pseudo Labels for Music Source Separation with Noisy Labeled Data