Bi-LSTM neural network for EEG-based error detection in musicians’ performance

Electroencephalography (EEG) is a tool that allows us to analyze brain activity with high temporal resolution. These measures, combined deep learning and digital signal processing, are widely used in neurological disorder detection emotion mental recognition. In this paper, new method for recognition presented: instantaneous frequency, spectral entropy Mel-frequency cepstral coefficients (MFCC) classify EEG signals using bidirectional LSTM neural networks. It shown can be intra-subject or inter-subject analysis has been applied error musician performance reaching compelling accuracy.