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

In the recent trend of semi-supervised speech recognition, bothself-supervised representation learning and pseudo-labeling have shownpromising results. In this paper, we propose a novel approach to combine theirideas for end-to-end speech recognition model. Without any extra loss function,we utilize the Gradient Mask to optimize the model when training onpseudo-label. This method forces the speech recognition model to predict fromthe masked input to learn strong acoustic representation and make trainingrobust to label noise. In our semi-supervised experiments, the method canimprove the model performance when training on pseudo-label and our methodachieved competitive results comparing with other semi-supervised approaches onthe Librispeech 100 hours experiments.

Improving Pseudo-label Training For End-to-end Speech Recognition Using Gradient Mask