RT Journal Article
SR Electronic
T1 Real-time decoding of selective attention from the human auditory brainstem response to continuous speech
JF bioRxiv
FD Cold Spring Harbor Laboratory
SP 259853
DO 10.1101/259853
A1 Octave Etard
A1 Mikolaj Kegler
A1 Chananel Braiman
A1 Antonio Elia Forte
A1 Tobias Reichenbach
YR 2018
UL http://biorxiv.org/content/early/2018/02/05/259853.abstract
AB Humans are highly skilled at analysing complex auditory scenes. Previously we showed that the auditory brainstem response to speech is modulated by selective attention, a result that we achieved through developing a novel method for measuring the brainstem’s response to running speech (Forte et al. 2017). Here we demonstrate that the attentional modulation of the brainstem response to speech can be employed to decode the attentional focus of a listener in real time, from short measurements of ten seconds or less in duration. The decoding is based on complex statistical models for extracting the brainstem response from multi-channel scalp recordings and subsequent classification of the model performances according to the focus of attention. We further show how a few recording channels as well as out-of-the-box decoding that employs population average models achieve a high accuracy from short recordings as well.