Continuous F0 in the source-excitation generation for HMM-based TTS: Do we need voiced/unvoiced classification?
Javier LatorreMark J. F. GalesSabine BuchholzKate KnillMasatsune TamuraYamato OhtaniMasami AkaminePublished in: ICASSP (2011)
Keyphrases
- machine learning
- classification systems
- hidden markov models
- pattern classification
- classification method
- classification algorithm
- text classification
- pattern recognition
- support vector machine
- support vector
- speech signal
- clustering algorithm
- preprocessing
- feature vectors
- classification accuracy
- class labels
- decision trees
- classification scheme
- feature selection
- classification process
- eeg signals
- numeric values
- automatic classification
- classification rules
- model selection
- image classification
- training set
- feature space
- feature extraction