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

ASR models often suffer from a long-form deletion problem where the modelpredicts sequential blanks instead of words when transcribing a lengthy audio(in the order of minutes or hours). From the perspective of a user ordownstream system consuming the ASR results, this behavior can be perceived asthe model "being stuck", and potentially make the product hard to use. One ofthe culprits for long-form deletion is training-test data mismatch, which canhappen even when the model is trained on diverse and large-scale data collectedfrom multiple application domains. In this work, we introduce a novel techniqueto simultaneously model different groups of speakers in the audio along withthe standard transcript tokens. Speakers are grouped as primary andnon-primary, which connects the application domains and significantlyalleviates the long-form deletion problem. This improved model neither needsany additional training data nor incurs additional training or inference cost.

Improved Long-Form Speech Recognition by Jointly Modeling the Primary and Non-primary Speakers