Segmental feature extraction and coding for speech synthesis.
Hiroshi OhmuraKazuyo TanakaPublished in: EUROSPEECH (1999)
Keyphrases
- speech synthesis
- feature extraction
- speech recognition
- text to speech
- hidden markov models
- vocal tract
- coding scheme
- linear predictive
- prosodic features
- pattern recognition
- preprocessing
- feature vectors
- coding method
- image processing
- pattern classification
- image classification
- principal component analysis
- face recognition
- feature representation
- inter frame
- extracting features
- dimensionality reduction
- linear feature extraction
- image preprocessing
- speech corpus
- discriminant analysis
- manifold learning
- dimension reduction
- linear discriminant analysis
- support vector machine svm
- bit rate
- wavelet transform
- feature space
- feature selection
- extracted features
- texture analysis
- coding efficiency
- computer vision
- error control
- feature set
- feature extractors
- bayesian networks