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

Research on speech-to-speech translation (S2ST) has progressed rapidly inrecent years. Many end-to-end systems have been proposed and show advantagesover conventional cascade systems, which are often composed of recognition,translation and synthesis sub-systems. However, most of the end-to-end systemsstill rely on intermediate textual supervision during training, which makes itinfeasible to work for languages without written forms. In this work, wepropose a novel model, Textless Translatotron, which is based on Translatotron2, for training an end-to-end direct S2ST model without any textualsupervision. Instead of jointly training with an auxiliary task predictingtarget phonemes as in Translatotron 2, the proposed model uses an auxiliarytask predicting discrete speech representations which are obtained from learnedor random speech quantizers. When a speech encoder pre-trained withunsupervised speech data is used for both models, the proposed model obtainstranslation quality nearly on-par with Translatotron 2 on the multilingualCVSS-C corpus as well as the bilingual Fisher Spanish-English corpus. On thelatter, it outperforms the prior state-of-the-art textless model by +18.5 BLEU.

Textless Direct Speech-to-Speech Translation with Discrete Speech Representation