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

Multilingual speech recognition for both monolingual and code-switchingspeech is a challenging task. Recently, based on the Mixture of Experts (MoE),many works have made good progress in multilingual and code-switching ASR, butpresent huge computational complexity with the increase of supported languages.In this work, we propose a computation-efficient network named Language-RoutingMixture of Experts (LR-MoE) for multilingual and code-switching ASR. LR-MoEextracts language-specific representations through the Mixture of LanguageExperts (MLE), which is guided to learn by a frame-wise language routingmechanism. The weight-shared frame-level language identification (LID) networkis jointly trained as the shared pre-router of each MoE layer. Experiments showthat the proposed method significantly improves multilingual and code-switchingspeech recognition performances over baseline with comparable computationalefficiency.

Language-Routing Mixture of Experts for Multilingual and Code-Switching Speech Recognition