Phoneme-guided Dysarthric speech conversion With non-parallel data by joint training.
Xunquan ChenAtsuki OshiroJinhui ChenRyoichi TakashimaTetsuya TakiguchiPublished in: Signal Image Video Process. (2022)
Keyphrases
- data sets
- small number
- synthetic data
- statistical analysis
- high quality
- data collection
- computer systems
- training dataset
- parallel processing
- raw data
- speech recognition
- training examples
- training samples
- data mining techniques
- probability distribution
- data analysis
- neural network
- knowledge discovery
- high dimensional data
- data points
- data quality
- data structure