Decoding Musical Timbre Perception from Single-Trial EEG Data

Many users of hearing aids report challenges when listening to music. In the future, it may be possible to develop hearing aids that have electrodes which monitors brain activity in real-time and adapts the filters on the hearing aid to match the volitions of the user. In music, this could mean amplifying the sound of the instrument the listener wants to hear. One of the first steps in this research is to determine if a machine learning algorithm can identify to which instrument an individual is listening based only on a brief EEG signal. To test this possibility, participants were presented with a series of brief tones that varied in timbre (Trombone, Clarinet’ Cello, Piano and Pure Tone) while their ongoing EEG was recorded from 73 electrodes. Linear Discriminant Analysis (LDA) was used. We investigated four different sets of features - Raw EEG, ERP-based features, Harmonics-based features and Regularity-based features. The Raw EEG based classifier performed significantly above chance (37%) when attempting to distinguish between responses to different musical instruments for 5-way classification. More advanced classification algorithms or different features may be able to better distinguish between tones with a musical timbre.