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

Contextual spelling correction models are an alternative to shallow fusion toimprove automatic speech recognition (ASR) quality given user vocabulary. Todeal with large user vocabularies, most of these models include candidateretrieval mechanisms, usually based on minimum edit distance between fragmentsof ASR hypothesis and user phrases. However, the edit-distance approach isslow, non-trainable, and may have low recall as it relies only on commonletters. We propose: 1) a novel algorithm for candidate retrieval, based onmisspelled n-gram mappings, which gives up to 90% recall with just the top 10candidates on Spoken Wikipedia; 2) a non-autoregressive neural model based onBERT architecture, where the initial transcript and ten candidates are combinedinto one input. The experiments on Spoken Wikipedia show 21.4% word error rateimprovement compared to a baseline ASR system.

SpellMapper: A non-autoregressive neural spellchecker for ASR customization with candidate retrieval based on n-gram mappings