Feature extraction for speech recognition based on orthogonal acoustic-feature planes and LDA.
Tsuneo NittaPublished in: ICASSP (1999)
Keyphrases
- speech recognition
- feature extraction
- speech recognition systems
- cepstral coefficients
- linear discriminant analysis
- speaker independent
- pattern recognition
- feature vectors
- speaker identification
- speech recognizers
- face recognition
- feature set
- mel frequency cepstral coefficients
- discriminant analysis
- principal component analysis
- speech synthesis
- speech signal
- language model
- automatic speech recognition
- noisy speech
- hidden markov models
- speech processing
- acoustic models
- speech recognizer
- dimensionality reduction
- audio signal
- acoustic features
- image classification
- noisy environments
- feature space
- speech recognition technology
- frequency domain
- generative model
- feature selection
- image processing
- speaker recognition
- speaker dependent
- support vector machine
- isolated word
- audio visual speech recognition
- gaussian mixture model
- topic models
- wavelet transform
- probabilistic model