Wavelet feature selection of audio and imagined/vocalized EEG signals for ANN based multimodal ASR system.
P. P. MiniTessamma ThomasR. GopikakumariPublished in: Biomed. Signal Process. Control. (2021)
Keyphrases
- eeg signals
- feature selection
- eeg data
- signal processing
- linear discriminant classifier
- audio visual
- multimedia
- multimodal fusion
- multimodal information
- artificial neural networks
- brain computer interface
- wavelet transform
- cross modal
- automatic speech recognition
- motor imagery
- multi modal
- feature extraction
- healthy subjects
- wavelet coefficients
- denoising
- feature set
- multi stream
- independent component analysis
- visual information
- classification accuracy
- mutual information
- broadcast news
- feature space
- visual data
- feature subset
- multimodal interaction
- event related potentials
- support vector
- machine learning
- speech recognition
- multiresolution
- pattern recognition
- multiscale
- brain activity
- feed forward neural networks
- spontaneous speech
- music information retrieval
- noisy environments
- image processing
- speech signal
- spectral features
- knn
- electrical activity
- image analysis
- kernel density estimators