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

The black-box nature of end-to-end speech translation (E2E ST) systems makesit difficult to understand how source language inputs are being mapped to thetarget language. To solve this problem, we would like to simultaneouslygenerate automatic speech recognition (ASR) and ST predictions such that eachsource language word is explicitly mapped to a target language word. A majorchallenge arises from the fact that translation is a non-monotonic sequencetransduction task due to word ordering differences between languages -- thisclashes with the monotonic nature of ASR. Therefore, we propose to generate STtokens out-of-order while remembering how to re-order them later. We achievethis by predicting a sequence of tuples consisting of a source word, thecorresponding target words, and post-editing operations dictating the correctinsertion points for the target word. We examine two variants of such operationsequences which enable generation of monotonic transcriptions and non-monotonictranslations from the same speech input simultaneously. We apply our approachto offline and real-time streaming models, demonstrating that we can provideexplainable translations without sacrificing quality or latency. In fact, thedelayed re-ordering ability of our approach improves performance duringstreaming. As an added benefit, our method performs ASR and ST simultaneously,making it faster than using two separate systems to perform these tasks.

Align, Write, Re-order: Explainable End-to-End Speech Translation via Operation Sequence Generation