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

Exploiting cross-lingual resources is an effective way to compensate for datascarcity of low resource languages. Recently, a novel multilingual model fusiontechnique has been proposed where a model is trained to learn cross-lingualacoustic-phonetic similarities as a mapping function. However, handcraftedlexicons have been used to train hybrid DNN-HMM ASR systems. To remove thisdependency, we extend the concept of learnable cross-lingual mappings forend-to-end speech recognition. Furthermore, mapping models are employed totransliterate the source languages to the target language without usingparallel data. Finally, the source audio and its transliteration is used fordata augmentation to retrain the target language ASR. The results show that anysource language ASR model can be used for a low-resource target languagerecognition followed by proposed mapping model. Furthermore, data augmentationresults in a relative gain up to 5% over baseline monolingual model.

Learning Cross-lingual Mappings for Data Augmentation to Improve Low-Resource Speech Recognition