TTS-by-TTS: TTS-Driven Data Augmentation for Fast and High-Quality Speech Synthesis.
Min-Jae HwangRyuichi YamamotoEunwoo SongJae-Min KimPublished in: ICASSP (2021)
Keyphrases
- text to speech
- high quality
- speech synthesis
- data sets
- image data
- data quality
- synthetic data
- data processing
- input data
- data collection
- knowledge discovery
- original data
- complex data
- training data
- experimental data
- raw data
- database
- prosodic features
- data mining techniques
- data points
- data sources
- data analysis
- computer vision
- small number
- statistical analysis
- sensor data
- probability distribution
- data distribution
- xml documents
- data objects
- data streams
- social networks
- neural network