Detection of Speech Impairments Using Cepstrum, Auditory Spectrogram and Wavelet Time Scattering Domain Features.
Andrius LauraitisRytis MaskeliunasRobertas DamaseviciusTomas KrilaviciusPublished in: IEEE Access (2020)
Keyphrases
- false positives
- feature extraction
- low level
- image features
- speech signal
- feature vectors
- feature set
- denoising
- detection method
- domain specific
- linear predictive coding
- feature selection
- multiscale
- wavelet transform
- classification accuracy
- signal processing
- object recognition
- speech recognition
- pattern recognition
- wavelet domain
- audio visual
- feature extraction and classification
- lexical features
- energy distribution
- image processing