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: INTERSPEECH (2022)
Keyphrases
- text to speech
- speech synthesis
- data sets
- support vector machine
- database
- training data
- high quality
- data sources
- data processing
- synthetic data
- data structure
- data analysis
- neural network
- input data
- data collection
- spatial data
- data mining techniques
- raw data
- radial basis function
- training samples
- feature selection
- image data
- artificial neural networks
- image segmentation