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

Many studies have examined the shortcomings of word error rate (WER) as anevaluation metric for automatic speech recognition (ASR) systems. Since WERconsiders only literal word-level correctness, new evaluation metrics based onsemantic similarity such as semantic distance (SD) and BERTScore have beendeveloped. However, we found that these metrics have their own limitations,such as a tendency to overly prioritise keywords. We propose H_eval, a newhybrid evaluation metric for ASR systems that considers both semanticcorrectness and error rate and performs significantly well in scenarios whereWER and SD perform poorly. Due to lighter computation compared to BERTScore, itoffers 49 times reduction in metric computation time. Furthermore, we show thatH_eval correlates strongly with downstream NLP tasks. Also, to reduce themetric calculation time, we built multiple fast and lightweight models usingdistillation techniques

H_eval: A new hybrid evaluation metric for automatic speech recognition tasks