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

Neuro-steered speaker extraction aims to extract the listener'sbrain-attended speech signal from a multi-talker speech signal, in which theattention is derived from the cortical activity. This activity is usuallyrecorded using electroencephalography (EEG) devices. Though promising, currentmethods often have a high speaker confusion error, where the interferingspeaker is extracted instead of the attended speaker, degrading the listeningexperience. In this work, we aim to reduce the speaker confusion error in theneuro-steered speaker extraction model through a jointly fine-tuned auxiliaryauditory attention detection model. The latter reinforces the consistencybetween the extracted target speech signal and the EEG representation, and alsoimproves the EEG representation. Experimental results show that the proposednetwork significantly outperforms the baseline in terms of speaker confusionand overall signal quality in two-talker scenarios.

NeuroHeed+: Improving Neuro-steered Speaker Extraction with Joint Auditory Attention Detection