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

In end-to-end speech translation, speech and text pre-trained models improvetranslation quality. Recently proposed models simply connect the pre-trainedmodels of speech and text as encoder and decoder. Therefore, only theinformation from the final layer of encoders is input to the decoder. Since itis clear that the speech pre-trained model outputs different information fromeach layer, the simple connection method cannot fully utilize the informationthat the speech pre-trained model has. In this study, we propose aninter-connection mechanism that aggregates the information from each layer ofthe speech pre-trained model by weighted sums and inputs into the decoder. Thismechanism increased BLEU by approximately 2 points in en-de, en-ja, and en-zhby increasing parameters by 2K when the speech pre-trained model was frozen.Furthermore, we investigated the contribution of each layer for each languageby visualizing layer weights and found that the contributions were different.

Inter-connection: Effective Connection between Pre-trained Encoder and Decoder for Speech Translation