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

We compare features for dynamic time warping (DTW) when used to bootstrapkeyword spotting (KWS) in an almost zero-resource setting. Suchquickly-deployable systems aim to support United Nations (UN) humanitarianrelief efforts in parts of Africa with severely under-resourced languages. Ourobjective is to identify acoustic features that provide acceptable KWSperformance in such environments. As supervised resource, we restrict ourselvesto a small, easily acquired and independently compiled set of isolatedkeywords. For feature extraction, a multilingual bottleneck feature (BNF)extractor, trained on well-resourced out-of-domain languages, is integratedwith a correspondence autoencoder (CAE) trained on extremely sparse in-domaindata. On their own, BNFs and CAE features are shown to achieve a more than 2%absolute performance improvement over baseline MFCCs. However, by using BNFs asinput to the CAE, even better performance is achieved, with a more than 11%absolute improvement in ROC AUC over MFCCs and more than twice as many top-10retrievals for two evaluated languages, English and Luganda. We conclude thatintegrating BNFs with the CAE allows both large out-of-domain and sparsein-domain resources to be exploited for improved ASR-free keyword spotting.

Feature exploration for almost zero-resource ASR-free keyword spotting using a multilingual bottleneck extractor and correspondence autoencoders