Creating expressive synthetic voices by unsupervised clustering of audiobooks.
Igor JaukAntonio BonafontePaula Lopez-OteroLaura Docío FernándezPublished in: INTERSPEECH (2015)
Keyphrases
- unsupervised clustering
- supervised classification
- clustering method
- clustering algorithm
- image segmentation
- semi supervised clustering
- k means
- spectral clustering
- fuzzy c means
- semi supervised clustering algorithm
- pairwise constraints
- image processing
- high dimensional
- dimensionality reduction
- text categorization