In Other News: a Bi-style Text-to-speech Model for Synthesizing Newscaster Voice with Limited Data.
Nishant PrateekMateusz LajszczakRoberto Barra-ChicoteThomas DrugmanJaime Lorenzo-TruebaThomas MerrittSrikanth RonankiTrevor WoodPublished in: NAACL-HLT (2) (2019)
Keyphrases
- text to speech
- experimental data
- data sets
- input data
- test data
- prior knowledge
- probabilistic model
- data analysis
- probability distribution
- measured data
- empirical data
- data processing
- image data
- high level
- database
- simulation data
- raw data
- network structure
- computational model
- synthetic data
- similarity measure
- end users
- data collection
- neural network model
- learned models
- data points
- training data