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

Deep-learning based speech separation models confront poor generalizationproblem that even the state-of-the-art models could abruptly fail whenevaluating them in mismatch conditions. To address this problem, we propose aneasy-to-implement yet effective consistency based semi-supervised learning(SSL) approach, namely Mixup-Breakdown training (MBT). It learns a teachermodel to "breakdown" unlabeled inputs, and the estimated separations areinterpolated to produce more useful pseudo "mixup" input-output pairs, on whichthe consistency regularization could apply for learning a student model. In ourexperiment, we evaluate MBT under various conditions with ascending degrees ofmismatch, including unseen interfering speech, noise, and music, and compareMBT's generalization capability against state-of-the-art supervised learningand SSL approaches. The result indicates that MBT significantly outperformsseveral strong baselines with up to 13.77% relative SI-SNRi improvement.Moreover, MBT only adds negligible computational overhead to standard trainingschemes.

Mixup-breakdown: a consistency training method for improving generalization of speech separation models