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/

Zendy Plus

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

Zendy Tools

Zendy Open

Contextual ASR, which takes a list of bias terms as input along with audio,has drawn recent interest as ASR use becomes more widespread. We are releasingcontextual biasing lists to accompany the Earnings21 dataset, creating a publicbenchmark for this task. We present baseline results on this benchmark using apretrained end-to-end ASR model from the WeNet toolkit. We show results forshallow fusion contextual biasing applied to two different decoding algorithms.Our baseline results confirm observations that end-to-end models struggle inparticular with words that are rarely or never seen during training, and thatexisting shallow fusion techniques do not adequately address this problem. Wepropose an alternate spelling prediction model that improves recall of rarewords by 34.7% relative and of out-of-vocabulary words by 97.2% relative,compared to contextual biasing without alternate spellings. This model isconceptually similar to ones used in prior work, but is simpler to implement asit does not rely on either a pronunciation dictionary or an existingtext-to-speech system.

Improving Contextual Recognition of Rare Words with an Alternate Spelling Prediction Model