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

Trigger-word detection plays an important role as the entry point of user'scommunication with voice assistants. But supporting a particular word as atrigger-word involves huge amount of data collection, augmentation andlabelling for that word. This makes supporting new trigger-words a tedious andtime consuming process. To combat this, we explore the use of contrastivelearning as a pre-training task that helps the detection model to generalize todifferent words and noise conditions. We explore supervised contrastivetechniques and also propose a novel self-supervised training technique usingchunked words from long sentence audios. We show that both supervised and thenew self-supervised contrastive pre-training techniques have comparable resultsto a traditional classification pre-training on new trigger words with lessdata availability.

Towards noise robust trigger-word detection with contrastive learning pre-task for fast on-boarding of new trigger-words