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/

Zendy Plus

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

Zendy Tools

Zendy Open

Many people with hearing loss struggle to comprehend speech in crowdedauditory scenes, even when they are using hearing aids. It has recently beendemonstrated that the focus of a listener's selective attention to speech canbe decoded from their electroencephalography (EEG) recordings, raising theprospect of smart EEG-steered hearing aids which restore speech comprehensionin adverse acoustic environments (such as the cocktail party). To this end, wehere assess the feasibility of using a novel, ultra-wearable ear-EEG device toclassify the selective attention of normal-hearing listeners who participatedin a two-talker competing-speakers experiment.  Eighteen participants took part in a diotic listening task, whereby they wereasked to attend to one narrator whilst ignoring the other. Encoding models wereestimated from the recorded signals, and these confirmed that the device hasthe ability to capture auditory responses that are consistent with thosereported in high-density EEG studies. Several state-of-the-art auditoryattention decoding algorithms were next compared, includingstimulus-reconstruction algorithms based on linear regression as well asnon-linear deep neural networks, and canonical correlation analysis (CCA).  Meaningful markers of selective auditory attention could be extracted fromthe ear-EEG signals of all 18 participants, even when those markers werederived from relatively short EEG segments of just five seconds in duration.Algorithms which related the EEG signals to the rising edges of the speechtemporal envelope (onset envelope) were more successful than those which madeuse of the temporal envelope itself. The CCA algorithm achieved the highestmean attention decoding accuracy, although differences between the performancesof the three algorithms were both small and not statistically significant whenEEG segments of short durations were employed.

Comparison of linear and nonlinear methods for decoding selective attention to speech from ear-EEG recordings