Selection and Training Schemes for Improving TTS Voice Built on Found Data.
Fang-Yu KuoIris Chuoying OuyangSandesh AryalPierre LanchantinPublished in: INTERSPEECH (2019)
Keyphrases
- data sets
- data processing
- database
- original data
- genetic algorithm
- data collection
- image data
- missing data
- raw data
- computer systems
- data quality
- end users
- data sources
- data analysis
- data structure
- high quality
- training data
- historical data
- network structure
- text to speech
- synthetic data
- high dimensional data
- statistical analysis
- cloud computing
- data points
- hidden markov models
- learning algorithm