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

Joint speech-language training is challenging due to the large demand fortraining data and GPU consumption, as well as the modality gap between speechand language. We present ComSL, a speech-language model built atop a compositearchitecture of public pretrained speech-only and language-only models andoptimized data-efficiently for spoken language tasks. Particularly, we proposeto incorporate cross-modality learning into transfer learning and conduct themsimultaneously for downstream tasks in a multi-task learning manner. Ourapproach has demonstrated effectiveness in end-to-end speech-to-texttranslation tasks, achieving a new state-of-the-art average BLEU score of 31.5on the multilingual speech to English text translation task for 21 languages,as measured on the public CoVoST2 evaluation set.

ComSL: A Composite Speech-Language Model for End-to-End Speech-to-Text Translation