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

How to solve the data scarcity problem for end-to-end speech-to-texttranslation (ST)? It's well known that data augmentation is an efficient methodto improve performance for many tasks by enlarging the dataset. In this paper,we propose Mix at three levels for Speech Translation (M^3ST) method toincrease the diversity of the augmented training corpus. Specifically, weconduct two phases of fine-tuning based on a pre-trained model using externalmachine translation (MT) data. In the first stage of fine-tuning, we mix thetraining corpus at three levels, including word level, sentence level and framelevel, and fine-tune the entire model with mixed data. At the second stage offine-tuning, we take both original speech sequences and original text sequencesin parallel into the model to fine-tune the network, and use Jensen-Shannondivergence to regularize their outputs. Experiments on MuST-C speechtranslation benchmark and analysis show that M^3ST outperforms current strongbaselines and achieves state-of-the-art results on eight directions with anaverage BLEU of 29.9.

M3ST: Mix at Three Levels for Speech Translation