speech neuromuscular decoding based on spectrogram images using conformal predictors with bi-lstm文献.pdf
Neurocomputing 451 (2021) 25–34 Contents lists available at Scien improve the decoding performance by representing time series signals as spectrograms and utilising Keywords: Inductive Conformal Prediction (ICP) to provide predictions with confidence. All EMG data are recorded Speech articulatory activities Surface electromyography on six dedicated facial muscles while participants recite the displayed words subvocally. Three pre- Spectrogram trained convolutional models of MobileNet-V1, ResNet18 and Xception are used to extract features from Bidirectional LSTM spectrograms for classification. Both bidirectional Long-Short Time Memory (Bi-LSTM) and Gate Inductive conformal prediction Recurrent Unit (GRU) classifiers are used for prediction. Furthermore, an ICP decoder based on Bi- LSTM is built to provide guaranteed predictions for each example at a specified confidence level. The pro- posed method of combining feature extraction based on Xception and classification using Bi-LSTM gives a higher accura
speech neuromuscular decoding based on spectrogram images using conformal predictors with bi-lstm文献 来自淘豆网m.daumloan.com转载请标明出处.