Unsupervised Learning for Multi-Style Speech Synthesis with Limited Data.
Shuang LiangChenfeng MiaoMinchuan ChenJun MaShaojun WangJing XiaoPublished in: ICASSP (2021)
Keyphrases
- text to speech
- speech synthesis
- unsupervised learning
- data collection
- database
- data analysis
- input data
- data sets
- image data
- training data
- sensor data
- statistical analysis
- data sources
- data points
- neural network
- data objects
- computer systems
- raw data
- experimental data
- missing data
- machine learning
- feature selection
- data processing
- image processing
- data mining techniques
- prior knowledge