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

Speech translation for subtitling (SubST) is the task of automaticallytranslating speech data into well-formed subtitles by inserting subtitle breakscompliant to specific displaying guidelines. Similar to speech translation(ST), model training requires parallel data comprising audio inputs paired withtheir textual translations. In SubST, however, the text has to be alsoannotated with subtitle breaks. So far, this requirement has represented abottleneck for system development, as confirmed by the dearth of publiclyavailable SubST corpora. To fill this gap, we propose a method to convertexisting ST corpora into SubST resources without human intervention. We build asegmenter model that automatically segments texts into proper subtitles byexploiting audio and text in a multimodal fashion, achieving high segmentationquality in zero-shot conditions. Comparative experiments with SubST systemsrespectively trained on manual and automatic segmentations result in similarperformance, showing the effectiveness of our approach.

Dodging the Data Bottleneck: Automatic Subtitling with Automatically Segmented ST Corpora