Abstract
In a multi-speaker scenario, the human auditory system is able to attend to one particular speaker of interest and ignore the others. It has been demonstrated that it is possible to use electroencephalography (EEG) signals to infer to which speaker someone is attending by relating the neural activity to the speech signals. However, classifying auditory attention within a short time interval remains the main challenge. We present a convolutional neural network-based approach to extract the locus of auditory attention (left/right) without knowledge of the speech envelopes. Our results show that it is possible to decode the locus of attention within 1-2 s, with a median accuracy of around 81%. These results are promising for neuro-steered noise suppression in hearing aids, in particular in scenarios where per-speaker envelopes are unavailable.
Highlights
In a multi-speaker scenario, the human auditory system is able to focus on just one speaker, ignoring all other speakers and noise
To capture the general performance of the convolutional neural networks (CNNs), the reported accuracy for each subject is the mean accuracy of 10 different training runs of the model, each with a different initialization
We investigated how well the CNN performs on subjects that were not part of the training set
Summary
In a multi-speaker scenario, the human auditory system is able to focus on just one speaker, ignoring all other speakers and noise. This situation is called the ‘cocktail party problem’ (Cherry, 1953). This problem is mitigated by automatic noise suppression systems. When multiple speakers are present, these systems have to rely on heuristics such as the speaker volume or the listener’s look direction to determine the relevant speaker, which often fail in practice. This research finds applications in the development of neuro-steered hearing prostheses that analyze brain signals to automatically decode the direction or speaker to whom the user is attending, to subsequently amplify that specific speech stream while suppressing other speech streams and surrounding noise. The desired result is increased speech intelligibility for the listener
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
