UTTS: Unsupervised TTS with Conditional Disentangled Sequential Variational Auto-encoder.
Jiachen LianChunlei ZhangGopala Krishna AnumanchipalliDong YuPublished in: CoRR (2022)
Keyphrases
- text to speech
- rate distortion
- bit rate
- sequential data
- unsupervised learning
- random field model
- unsupervised manner
- image segmentation
- video compression
- video codec
- supervised classification
- model selection
- supervised learning
- semi supervised
- optical flow
- low complexity
- neural network
- image quality
- error control
- inter frame
- video coding
- optic flow
- variational framework
- optical flow computation
- power reduction
- wyner ziv video coding