Style Description based Text-to-Speech with Conditional Prosodic Layer Normalization based Diffusion GAN.
Neeraj KumarAnkur NarangBrejesh LallPublished in: CoRR (2023)
Keyphrases
- text to speech
- text to speech synthesis
- prosodic features
- speech synthesis
- high level
- programming tool
- anisotropic diffusion
- word processing
- english text
- application layer
- speaker verification
- writing skills
- structuring elements
- multi layer
- binary images
- preprocessing
- random field model
- pattern recognition
- image segmentation