TTS-by-TTS 2: Data-selective augmentation for neural speech synthesis using ranking support vector machine with variational autoencoder.
Eunwoo SongRyuichi YamamotoOhsung KwonChan-Ho SongMin-Jae HwangSuhyeon OhHyun-Wook YoonJin-Seob KimJae-Min KimPublished in: CoRR (2022)
Keyphrases
- text to speech
- speech synthesis
- training data
- data sets
- support vector machine
- data collection
- data quality
- raw data
- data sources
- data distribution
- input data
- synthetic data
- database
- missing data
- data structure
- image segmentation
- data processing
- speech recognition
- decision trees
- artificial neural networks
- image acquisition
- feature selection
- high quality