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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Direct speech-to-speech translation (S2ST) is an attractive research topicwith many advantages compared to cascaded S2ST. However, direct S2ST suffersfrom the data scarcity problem because the corpora from speech of the sourcelanguage to speech of the target language are very rare. To address this issue,we propose in this paper a Speech2S model, which is jointly pre-trained withunpaired speech and bilingual text data for direct speech-to-speech translationtasks. By effectively leveraging the paired text data, Speech2S is capable ofmodeling the cross-lingual speech conversion from source to target language. Weverify the performance of the proposed Speech2S on Europarl-ST and VoxPopulidatasets. Experimental results demonstrate that Speech2S gets an improvement ofabout 5 BLEU scores compared to encoder-only pre-training models, and achievesa competitive or even better performance than existing state-of-the-artmodels1.

Joint Pre-Training with Speech and Bilingual Text for Direct Speech to Speech Translation