Back

Shaping Sounds with P300 Based Brain-Computer Musical Interface

Akkaya, U. C.; Demirel, C.; de Latour, R.; Ince, G.

2022-06-17 neuroscience
10.1101/2022.06.13.495880 bioRxiv
Show abstract

This paper describes the development and testing of a brain-computer musical interface (BCMI) that allows a user to select and transform one element of a musical texture by paying attention to that particular element. In order to realize the BCMI system mentioned, a comprehensive testing scheme was established which uses auditory evoked potentials to elicit P300 waves via averaging various types of stimuli. Resented sound stimuli were divided into multi-channel speaker setups to have better localization of user-focused sound stimuli. A sound synthesis model was developed for transforming its sound texture based on neural oscillations that were categorized with the help of a self-organizing map algorithm. In addition, an artificial neural network was used to predict the possible P300 waves that show the attentional focus of a subject. Most of the P300 waves were classified successfully for most of the participants. Promising results were achieved concerning the developed BCMI system. A neural network model was also utilized to predict the possible P300 waves, which show the subjects selective attention. The majority of the participants were able to correctly classify P300 waves. The proposed BCMI system yielded promising results.

Matching journals

The top 9 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.