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

Mixture-of-experts based models, which use language experts to extractlanguage-specific representations effectively, have been well applied incode-switching automatic speech recognition. However, there is stillsubstantial space to improve as similar pronunciation across languages mayresult in ineffective multi-language modeling and inaccurate language boundaryestimation. To eliminate these drawbacks, we propose a cross-layer languageadapter and a boundary-aware training method, namely Boundary-AwareMixture-of-Experts (BA-MoE). Specifically, we introduce language-specificadapters to separate language-specific representations and a unified gatinglayer to fuse representations within each encoder layer. Second, we computelanguage adaptation loss of the mean output of each language-specific adapterto improve the adapter module's language-specific representation learning.Besides, we utilize a boundary-aware predictor to learn boundaryrepresentations for dealing with language boundary confusion. Our approachachieves significant performance improvement, reducing the mixture error rateby 16.55\% compared to the baseline on the ASRU 2019 Mandarin-Englishcode-switching challenge dataset.

BA-MoE: Boundary-Aware Mixture-of-Experts Adapter for Code-Switching Speech Recognition