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 a pipeline speech translation system, automatic speech recognition (ASR)system will transmit errors in recognition to the downstream machinetranslation (MT) system. A standard machine translation system is usuallytrained on parallel corpus composed of clean text and will perform poorly ontext with recognition noise, a gap well known in speech translation community.In this paper, we propose a training architecture which aims at making a neuralmachine translation model more robust against speech recognition errors. Ourapproach addresses the encoder and the decoder simultaneously using adversariallearning and data augmentation, respectively. Experimental results on IWSLT2018speech translation task show that our approach can bridge the gap between theASR output and the MT input, outperforms the baseline by up to 2.83 BLEU onnoisy ASR output, while maintaining close performance on clean text.

Breaking the Data Barrier: Towards Robust Speech Translation via Adversarial Stability Training