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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Navigating the challenges of data-driven speech processing, one of theprimary hurdles is accessing reliable pathological speech data. While publicdatasets appear to offer solutions, they come with inherent risks of potentialunintended exposure of patient health information via re-identificationattacks. Using a comprehensive real-world pathological speech corpus, with overn=3,800 test subjects spanning various age groups and speech disorders, weemployed a deep-learning-driven automatic speaker verification (ASV) approach.This resulted in a notable mean equal error rate (EER) of 0.89% with a standarddeviation of 0.06%, outstripping traditional benchmarks. Our comprehensiveassessments demonstrate that pathological speech overall faces heightenedprivacy breach risks compared to healthy speech. Specifically, adults withdysphonia are at heightened re-identification risks, whereas conditions likedysarthria yield results comparable to those of healthy speakers. Crucially,speech intelligibility does not influence the ASV system's performance metrics.In pediatric cases, particularly those with cleft lip and palate, the recordingenvironment plays a decisive role in re-identification. Merging data acrosspathological types led to a marked EER decrease, suggesting the potentialbenefits of pathological diversity in ASV, accompanied by a logarithmic boostin ASV effectiveness. In essence, this research sheds light on the dynamicsbetween pathological speech and speaker verification, emphasizing its crucialrole in safeguarding patient confidentiality in our increasingly digitizedhealthcare era.

The effect of speech pathology on automatic speaker verification -- a large-scale study