Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis.
Ye JiaYu ZhangRon J. WeissQuan WangJonathan ShenFei RenZhifeng ChenPatrick NguyenRuoming PangIgnacio Lopez-MorenoYonghui WuPublished in: CoRR (2018)
Keyphrases
- transfer learning
- speaker verification
- text to speech synthesis
- noisy environments
- text to speech
- knowledge transfer
- labeled data
- cross domain
- reinforcement learning
- active learning
- collaborative filtering
- machine learning
- text categorization
- audio visual
- text classification
- target domain
- learning algorithm
- semi supervised learning
- multilayer perceptron
- language identification
- machine learning algorithms
- using artificial neural networks
- emotion recognition
- image processing
- face verification
- artificial neural networks
- data sets
- training set
- fuzzy logic
- text mining
- edge detection
- unsupervised learning