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 systems based on deep learning are mainlytrained under empirical risk minimization (ERM). Since ERM utilizes theaveraged performance on the data samples regardless of a group such as healthyor dysarthric speakers, ASR systems are unaware of the performance disparitiesacross the groups. This results in biased ASR systems whose performancedifferences among groups are severe. In this study, we aim to improve the ASRsystem in terms of group robustness for dysarthric speakers. To achieve ourgoal, we present a novel approach, sample reweighting with sample affinity test(Re-SAT). Re-SAT systematically measures the debiasing helpfulness of the givendata sample and then mitigates the bias by debiasing helpfulness-based samplereweighting. Experimental results demonstrate that Re-SAT contributes toimproved ASR performance on dysarthric speech without performance degradationon healthy speech.

Debiased Automatic Speech Recognition for Dysarthric Speech via Sample Reweighting with Sample Affinity Test