A Revisit to Feature Handling for High-quality Voice Conversion Based on Gaussian Mixture Model.
Hitoshi SudaGaku KotaniShinnosuke TakamichiDaisuke SaitoPublished in: APSIPA (2018)
Keyphrases
- gaussian mixture model
- high quality
- feature vectors
- mixture model
- speaker recognition
- em algorithm
- gaussian mixture
- image features
- maximum likelihood
- background subtraction
- gaussian mixture modeling
- speaker identification
- expectation maximization
- gaussian model
- gaussian distribution
- feature space
- learning algorithm
- wavelet transform
- high resolution
- feature representation
- multiscale
- similarity measure
- image sequences
- feature selection