VAENAR-TTS: Variational Auto-Encoder based Non-AutoRegressive Text-to-Speech Synthesis.
Hui LuZhiyong WuXixin WuXu LiShiyin KangXunying LiuHelen MengPublished in: CoRR (2021)
Keyphrases
- autoregressive
- text to speech
- text to speech synthesis
- non stationary
- moving average
- random fields
- bit rate
- image segmentation
- word processing
- gaussian markov random field
- autoregressive model
- optical flow
- sar images
- spectrum analysis
- motion estimation
- random field models
- machine learning
- image features
- multiresolution
- computational complexity
- image processing