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

Customized keyword spotting (KWS) has great potential to be deployed on edgedevices to achieve hands-free user experience. However, in real applications,false alarm (FA) would be a serious problem for spotting dozens or evenhundreds of keywords, which drastically affects user experience. To solve thisproblem, in this paper, we leverage the recent advances in transducer andtransformer based acoustic models and propose a new multi-stage customized KWSframework named Cascaded Transducer-Transformer KWS (CaTT-KWS), which includesa transducer based keyword detector, a frame-level phone predictor based forcealignment module and a transformer based decoder. Specifically, the streamingtransducer module is used to spot keyword candidates in audio stream. Thenforce alignment is implemented using the phone posteriors predicted by thephone predictor to finish the first stage keyword verification and refine thetime boundaries of keyword. Finally, the transformer decoder further verifiesthe triggered keyword. Our proposed CaTT-KWS framework reduces FA rateeffectively without obviously hurting keyword recognition accuracy.Specifically, we can get impressively 0.13 FA per hour on a challengingdataset, with over 90% relative reduction on FA comparing to the transducerbased detection model, while keyword recognition accuracy only drops less than2%.

CaTT-KWS: A Multi-stage Customized Keyword Spotting Framework based on Cascaded Transducer-Transformer