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

One challenge in speech translation is that plenty of spoken content islong-form, but short units are necessary for obtaining high-qualitytranslations. To address this mismatch, we adapt large language models (LLMs)to split long ASR transcripts into segments that can be independentlytranslated so as to maximize the overall translation quality. We overcome thetendency of hallucination in LLMs by incorporating finite-state constraintsduring decoding; these eliminate invalid outputs without requiring additionaltraining. We discover that LLMs are adaptable to transcripts containing ASRerrors through prompt-tuning or fine-tuning. Relative to a state-of-the-artautomatic punctuation baseline, our best LLM improves the average BLEU by 2.9points for English-German, English-Spanish, and English-Arabic TED talktranslation in 9 test sets, just by improving segmentation.

Long-Form Speech Translation through Segmentation with Finite-State Decoding Constraints on Large Language Models