A Method for Emotional Speech Synthesis Based on Speaker Adaptive Training.
Xiaoyong LuYanqin LiHongwu YangPublished in: ISCSLP (2018)
Keyphrases
- high accuracy
- dynamic programming
- training phase
- similarity measure
- cost function
- computational cost
- detection method
- training samples
- pairwise
- significant improvement
- data sets
- supervised learning
- speaker recognition
- training process
- high precision
- segmentation method
- model selection
- edge detection
- training set
- support vector
- genetic algorithm
- neural network