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

We propose an approach for pre-training speech representations via a maskedreconstruction loss. Our pre-trained encoder networks are bidirectional and cantherefore be used directly in typical bidirectional speech recognition models.The pre-trained networks can then be fine-tuned on a smaller amount ofsupervised data for speech recognition. Experiments with this approach on theLibriSpeech and Wall Street Journal corpora show promising results. We findthat the main factors that lead to speech recognition improvements are: maskingsegments of sufficient width in both time and frequency, pre-training on a muchlarger amount of unlabeled data than the labeled data, and domain adaptationwhen the unlabeled and labeled data come from different domains. The gain frompre-training is additive to that of supervised data augmentation.

Unsupervised Pre-training of Bidirectional Speech Encoders via Masked Reconstruction