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

Automatic speech recognition (ASR) systems often encounter difficulties inaccurately recognizing rare words, leading to errors that can have a negativeimpact on downstream tasks such as keyword spotting, intent detection, and textsummarization. To address this challenge, we present a novel ASR postprocessingmethod that focuses on improving the recognition of rare words through errordetection and context-aware error correction. Our method optimizes the decodingprocess by targeting only the predicted error positions, minimizing unnecessarycomputations. Moreover, we leverage a rare word list to provide additionalcontextual knowledge, enabling the model to better correct rare words.Experimental results across five datasets demonstrate that our proposed methodachieves significantly lower word error rates (WERs) than previous approacheswhile maintaining a reasonable inference speed. Furthermore, our approachexhibits promising robustness across different ASR systems.

ed-cec: improving rare word recognition using asr postprocessing based on error detection and context-aware error correction