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

End-to-end speech translation aims to translate speech in one language intotext in another language via an end-to-end way. Most existing methods employ anencoder-decoder structure with a single encoder to learn acousticrepresentation and semantic information simultaneously, which ignores thespeech-and-text modality differences and makes the encoder overloaded, leadingto great difficulty in learning such a model. To address these issues, wepropose a Speech-to-Text Adaptation for Speech Translation (STAST) model whichaims to improve the end-to-end model performance by bridging the modality gapbetween speech and text. Specifically, we decouple the speech translationencoder into three parts and introduce a shrink mechanism to match the lengthof speech representation with that of the corresponding text transcription. Toobtain better semantic representation, we completely integrate a text-basedtranslation model into the STAST so that two tasks can be trained in the samelatent space. Furthermore, we introduce a cross-modal adaptation method toclose the distance between speech and text representation. Experimental resultson English-French and English-German speech translation corpora have shown thatour model significantly outperforms strong baselines, and achieves the newstate-of-the-art performance.

Bridging the Modality Gap for Speech-to-Text Translation