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

Confidence estimation of predictions from an End-to-End (E2E) AutomaticSpeech Recognition (ASR) model benefits ASR's downstream and upstream tasks.Class-probability-based confidence scores do not accurately represent thequality of overconfident ASR predictions. An ancillary Confidence EstimationModel (CEM) calibrates the predictions. State-of-the-art (SOTA) solutions usebinary target scores for CEM training. However, the binary labels do not revealthe granular information of predicted words, such as temporal alignment betweenreference and hypothesis and whether the predicted word is entirely incorrector contains spelling errors. Addressing this issue, we propose a novelTemporal-Lexeme Similarity (TeLeS) confidence score to train CEM. To addressthe data imbalance of target scores while training CEM, we use shrinkage lossto focus on hard-to-learn data points and minimise the impact of easily learneddata points. We conduct experiments with ASR models trained in three languages,namely Hindi, Tamil, and Kannada, with varying training data sizes. Experimentsshow that TeLeS generalises well across domains. To demonstrate theapplicability of the proposed method, we formulate a TeLeS-based Acquisition(TeLeS-A) function for sampling uncertainty in active learning. We observe asignificant reduction in the Word Error Rate (WER) as compared to SOTA methods.

TeLeS: Temporal Lexeme Similarity Score to Estimate Confidence in End-to-End ASR