Natural language guidance of high-fidelity text-to-speech with synthetic annotations.
Daniel LythSimon KingPublished in: CoRR (2024)
Keyphrases
- high fidelity
- text to speech
- natural language
- speech synthesis
- real time
- text to speech synthesis
- prosodic features
- medical image compression
- high quality
- language processing
- programming tool
- real environment
- machine learning
- semantic analysis
- semantic annotation
- metadata
- high resolution
- dialogue system
- image annotation
- image analysis
- writing skills