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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

The paper describes a novel approach to Spoken Term Detection (STD) in largespoken archives using deep LSTM networks. The work is based on the previousapproach of using Siamese neural networks for STD and naturally extends it todirectly localize a spoken term and estimate its relevance score. The phonemeconfusion network generated by a phoneme recognizer is processed by the deepLSTM network which projects each segment of the confusion network into anembedding space. The searched term is projected into the same embedding spaceusing another deep LSTM network. The relevance score is then computed using asimple dot-product in the embedding space and calibrated using a sigmoidfunction to predict the probability of occurrence. The location of the searchedterm is then estimated from the sequence of output probabilities. The deep LSTMnetworks are trained in a self-supervised manner from paired recognitionhypotheses on word and phoneme levels. The method is experimentally evaluatedon MALACH data in English and Czech languages.

Spoken Term Detection and Relevance Score Estimation using Dot-Product of Pronunciation Embeddings