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 automatic speech recognition system, one of the difficultiesfor language expansion is the limited paired speech and text training data. Inthis paper, we propose a novel method to generate augmented samples withunpaired speech feature segments and text data for model pre-training, whichhas the advantage of low cost without using additional speech data. When mixing20,000 hours augmented speech data generated by our method with 12,500 hoursoriginal transcribed speech data for Italian Transformer transducer modelpre-training, we achieve 8.7% relative word error rate reduction. Thepre-trained model achieves similar performance as the model pre-trained withmultilingual transcribed 75,000 hours raw speech data. When merging theaugmented speech data with the multilingual data to pre-train a new model, weachieve even more relative word error rate reduction of 12.2% over thebaseline, which further verifies the effectiveness of our method for speechdata augmentation.

Pre-training End-to-end ASR Models with Augmented Speech Samples Queried by Text