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

Code-switching describes the practice of using more than one language in thesame sentence. In this study, we investigate how to optimize a neuraltransducer based bilingual automatic speech recognition (ASR) model forcode-switching speech. Focusing on the scenario where the ASR model is trainedwithout supervised code-switching data, we found that semi-supervised trainingand synthetic code-switched data can improve the bilingual ASR system oncode-switching speech. We analyze how each of the neural transducer's encoderscontributes towards code-switching performance by measuring encoder-specificrecall values, and evaluate our English/Mandarin system on the ASCEND data set.Our final system achieves 25% mixed error rate (MER) on the ASCENDEnglish/Mandarin code-switching test set -- reducing the MER by 2.1% absolutecompared to the previous literature -- while maintaining good accuracy on themonolingual test sets.

Optimizing Bilingual Neural Transducer with Synthetic Code-switching Text Generation