GMM Classification of Text-to-Speech Synthesis: Identification of Original Speaker's Voice.
Jiri PribilAnna PribilováJindrich MatousekPublished in: TSD (2014)
Keyphrases
- text to speech synthesis
- feature vectors
- classification accuracy
- mel frequency cepstral coefficients
- gaussian mixture model
- pattern recognition
- speaker recognition
- decision trees
- mixture model
- support vector machine svm
- automatic classification
- density estimation
- classification algorithm
- text classification
- neural network
- support vector machine
- image classification
- support vector
- feature selection
- information preserving
- machine learning
- speech recognition
- probabilistic model
- feature space
- speaker identification
- audio visual
- acoustic features
- text to speech
- extracting features
- pattern classification
- machine learning algorithms
- data sets
- training samples
- feature set