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/

Zendy Plus

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

Zendy Tools

Zendy Open

False triggers in voice assistants are unintended invocations of theassistant, which not only degrade the user experience but may also compromiseprivacy. False trigger mitigation (FTM) is a process to detect the falsetrigger events and respond appropriately to the user. In this paper, we proposea novel solution to the FTM problem by introducing a parallel ASR decodingprocess with a special language model trained from "out-of-domain" datasources. Such language model is complementary to the existing language modeloptimized for the assistant task. A bidirectional lattice RNN (Bi-LRNN)classifier trained from the lattices generated by the complementary languagemodel shows a $38.34\%$ relative reduction of the false trigger (FT) rate atthe fixed rate of $0.4\%$ false suppression (FS) of correct invocations,compared to the current Bi-LRNN model. In addition, we propose to train aparallel Bi-LRNN model based on the decoding lattices from both languagemodels, and examine various ways of implementation. The resulting model leadsto further reduction in the false trigger rate by $10.8\%$.

Complementary Language Model and Parallel Bi-LRNN for False Trigger Mitigation