An application of discriminative feature extraction to filter-bank-based speech recognition.
Alain BiemShigeru KatagiriErik McDermottBiing-Hwang JuangPublished in: IEEE Trans. Speech Audio Process. (2001)
Keyphrases
- speech recognition
- filter bank
- feature extraction
- frequency domain
- subband
- pattern recognition
- image coding
- wavelet transform
- feature vectors
- multiresolution
- hidden markov models
- signal processing
- language model
- speaker identification
- multiscale
- speech signal
- cepstral coefficients
- perfect reconstruction
- image processing
- speech synthesis
- automatic speech recognition
- noisy environments
- principal component analysis
- image classification
- speech recognizer
- wavelet packet
- feature selection
- speech recognition systems
- computationally efficient
- dimensionality reduction
- feature space
- face recognition
- texture features
- image compression
- extracted features
- feature set
- neural network
- wavelet decomposition
- gabor filters
- wavelet domain
- computer vision
- spatial domain
- discriminative training
- high frequency
- wavelet coefficients
- probabilistic model
- building blocks