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 Tools annual

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 monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

The electroencephalogram (EEG) offers a non-invasive means by which alistener's auditory system may be monitored during continuous speechperception. Reliable auditory-EEG decoders could facilitate the objectivediagnosis of hearing disorders, or find applications in cognitively-steeredhearing aids. Previously, we developed decoders for the ICASSP Auditory EEGSignal Processing Grand Challenge (SPGC). These decoders aimed to solve thematch-mismatch task: given a short temporal segment of EEG recordings, and twocandidate speech segments, the task is to identify which of the two speechsegments is temporally aligned, or matched, with the EEG segment. The decodersmade use of cortical responses to the speech envelope, as well asspeech-related frequency-following responses, to relate the EEG recordings tothe speech stimuli. Here we comprehensively document the methods by which thedecoders were developed. We extend our previous analysis by exploring theassociation between speaker characteristics (pitch and sex) and classificationaccuracy, and provide a full statistical analysis of the final performance ofthe decoders as evaluated on a heldout portion of the dataset. Finally, thegeneralisation capabilities of the decoders are characterised, by evaluatingthem using an entirely different dataset which contains EEG recorded under avariety of speech-listening conditions. The results show that thematch-mismatch decoders achieve accurate and robust classification accuracies,and they can even serve as auditory attention decoders without additionaltraining.

Decoding Envelope and Frequency-Following EEG Responses to Continuous Speech Using Deep Neural Networks