HAM-TTS: Hierarchical Acoustic Modeling for Token-Based Zero-Shot Text-to-Speech with Model and Data Scaling.
Chunhui WangChang ZengBowen ZhangZiyang MaYefan ZhuZifeng CaiJian ZhaoZhonglin JiangYong ChenPublished in: CoRR (2024)
Keyphrases
- text to speech
- data sets
- experimental data
- computational model
- probability distribution
- mathematical model
- data analysis
- input data
- simulation data
- image data
- data processing
- xml documents
- data sources
- data collection
- hierarchical model
- training data
- network structure
- measured data
- similarity measure
- models built
- modeling method
- pattern recognition
- data structure
- bayesian networks
- neural network model
- empirical data
- hierarchical structure
- modeling framework
- em algorithm
- probabilistic model