Hybrid NN/HMM-Based Speech Recognition with a Discriminant Neural Feature Extraction.
Daniel WillettGerhard RigollPublished in: NIPS (1997)
Keyphrases
- speech recognition
- feature extraction
- hidden markov models
- neural network
- discriminant analysis
- pattern recognition
- speaker identification
- principal component analysis
- cepstral coefficients
- speech signal
- automatic speech recognition
- speech processing
- language model
- feature vectors
- noisy environments
- nearest neighbor
- feature selection
- speaker independent
- face recognition
- speech recognizer
- knn
- feature space
- speech synthesis
- speech recognition systems
- speech understanding
- wavelet transform
- speech recognition technology
- isolated word
- image classification
- frequency domain
- artificial neural networks
- image processing
- signal processing
- speech retrieval
- handwriting recognition
- extracted features
- training process
- back propagation
- mel frequency cepstral coefficients
- speaker dependent
- speech recognizers
- information retrieval