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

This paper describes the submission of our end-to-end YiTrans speechtranslation system for the IWSLT 2022 offline task, which translates fromEnglish audio to German, Chinese, and Japanese. The YiTrans system is built onlarge-scale pre-trained encoder-decoder models. More specifically, we firstdesign a multi-stage pre-training strategy to build a multi-modality model witha large amount of labeled and unlabeled data. We then fine-tune thecorresponding components of the model for the downstream speech translationtasks. Moreover, we make various efforts to improve performance, such as datafiltering, data augmentation, speech segmentation, model ensemble, and so on.Experimental results show that our YiTrans system obtains a significantimprovement than the strong baseline on three translation directions, and itachieves +5.2 BLEU improvements over last year's optimal end-to-end system ontst2021 English-German. Our final submissions rank first on English-German andEnglish-Chinese end-to-end systems in terms of the automatic evaluation metric.We make our code and models publicly available.

The YiTrans End-to-End Speech Translation System for IWSLT 2022 Offline Shared Task