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

Human brain performs remarkably well in segregating a particular speaker frominterfering ones in a multi-speaker scenario. It has been recently shown thatwe can quantitatively evaluate the segregation capability by modelling therelationship between the speech signals present in an auditory scene and thecortical signals of the listener measured using electroencephalography (EEG).This has opened up avenues to integrate neuro-feedback into hearing aidswhereby the device can infer user's attention and enhance the attended speaker.Commonly used algorithms to infer the auditory attention are based on linearsystems theory where the speech cues such as envelopes are mapped on to the EEGsignals. Here, we present a joint convolutional neural network (CNN) - longshort-term memory (LSTM) model to infer the auditory attention. Our jointCNN-LSTM model takes the EEG signals and the spectrogram of the multiplespeakers as inputs and classifies the attention to one of the speakers. Weevaluated the reliability of our neural network using three different datasetscomprising of 61 subjects where, each subject undertook a dual-speakerexperiment. The three datasets analysed corresponded to speech stimulipresented in three different languages namely German, Danish and Dutch. Usingthe proposed joint CNN-LSTM model, we obtained a median decoding accuracy of77.2% at a trial duration of three seconds. Furthermore, we evaluated theamount of sparsity that our model can tolerate by means of magnitude pruningand found that the model can tolerate up to 50% sparsity without substantialloss of decoding accuracy.

Extracting the Auditory Attention in a Dual-Speaker Scenario from EEG using a Joint CNN-LSTM Model