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

Excessive sleepiness in attention-critical contexts can lead to adverseevents, such as car crashes. Detecting and monitoring sleepiness can helpprevent these adverse events from happening. In this paper, we use the Voiceomedataset to extract speech from 1,828 participants to develop a deep transferlearning model using Hidden-Unit BERT (HuBERT) speech representations to detectsleepiness from individuals. Speech is an under-utilized source of data insleep detection, but as speech collection is easy, cost-effective, andnon-invasive, it provides a promising resource for sleepiness detection. Twocomplementary techniques were conducted in order to seek converging evidenceregarding the importance of individual speech tasks. Our first technique,masking, evaluated task importance by combining all speech tasks, maskingselected responses in the speech, and observing systematic changes in modelaccuracy. Our second technique, separate training, compared the accuracy ofmultiple models, each of which used the same architecture, but was trained on adifferent subset of speech tasks. Our evaluation shows that the best-performingmodel utilizes the memory recall task and categorical naming task from theBoston Naming Test, which achieved an accuracy of 80.07% (F1-score of 0.85) and81.13% (F1-score of 0.89), respectively.

Speech Tasks Relevant to Sleepiness Determined with Deep Transfer Learning