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

In the realm of automatic speech recognition (ASR), the quest for models thatnot only perform with high accuracy but also offer transparency in theirdecision-making processes is crucial. The potential of quality estimation (QE)metrics is introduced and evaluated as a novel tool to enhance explainableartificial intelligence (XAI) in ASR systems. Through experiments and analyses,the capabilities of the NoRefER (No Reference Error Rate) metric are exploredin identifying word-level errors to aid post-editors in refining ASRhypotheses. The investigation also extends to the utility of NoRefER in thecorpus-building process, demonstrating its effectiveness in augmenting datasetswith insightful annotations. The diagnostic aspects of NoRefER are examined,revealing its ability to provide valuable insights into model behaviors anddecision patterns. This has proven beneficial for prioritizing hypotheses inpost-editing workflows and fine-tuning ASR models. The findings suggest thatNoRefER is not merely a tool for error detection but also a comprehensiveframework for enhancing ASR systems' transparency, efficiency, andeffectiveness. To ensure the reproducibility of the results, all source codesof this study are made publicly available.

Word-Level ASR Quality Estimation for Efficient Corpus Sampling and Post-Editing through Analyzing Attentions of a Reference-Free Metric