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 ON-TRAC Consortium translation systems developed fortwo challenge tracks featured in the Evaluation Campaign of IWSLT 2022:low-resource and dialect speech translation. For the Tunisian Arabic-Englishdataset (low-resource and dialect tracks), we build an end-to-end model as ourjoint primary submission, and compare it against cascaded models that leveragea large fine-tuned wav2vec 2.0 model for ASR. Our results show that in oursettings pipeline approaches are still very competitive, and that with the useof transfer learning, they can outperform end-to-end models for speechtranslation (ST). For the Tamasheq-French dataset (low-resource track) ourprimary submission leverages intermediate representations from a wav2vec 2.0model trained on 234 hours of Tamasheq audio, while our contrastive model usesa French phonetic transcription of the Tamasheq audio as input in a Conformerspeech translation architecture jointly trained on automatic speechrecognition, ST and machine translation losses. Our results highlight thatself-supervised models trained on smaller sets of target data are moreeffective to low-resource end-to-end ST fine-tuning, compared to largeoff-the-shelf models. Results also illustrate that even approximate phonetictranscriptions can improve ST scores.

ON-TRAC Consortium Systems for the IWSLT 2022 Dialect and Low-resource Speech Translation Tasks