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 Tools annual

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 monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Estimating confidence scores for recognition results is a classic task in ASRfield and of vital importance for kinds of downstream tasks and trainingstrategies. Previous end-to-end~(E2E) based confidence estimation models (CEM)predict score sequences of equal length with input transcriptions, leading tounreliable estimation when deletion and insertion errors occur. In this paperwe proposed CIF-Aligned confidence estimation model (CA-CEM) to achieveaccurate and reliable confidence estimation based on novel non-autoregressiveE2E ASR model - Paraformer. CA-CEM utilizes the modeling character ofcontinuous integrate-and-fire (CIF) mechanism to generate token-synchronousacoustic embedding, which solves the estimation failure issue above. We measurethe quality of estimation with AUC and RMSE in token level and ECE-U - aproposed metrics in utterance level. CA-CEM gains 24% and 19% relativereduction on ECE-U and also better AUC and RMSE on two test sets. Furthermore,we conduct analysis to explore the potential of CEM for different ASR relatedusage.

Accurate and Reliable Confidence Estimation Based on Non-Autoregressive End-to-End Speech Recognition System