A Neural Text-to-Speech Model Utilizing Broadcast Data Mixed with Background Music.
Hanbin BaeJae-Sung BaeYoung-Sun JooYoung-Ik KimHoon-Young ChoPublished in: CoRR (2021)
Keyphrases
- experimental data
- input data
- data sets
- simulation data
- prior knowledge
- text to speech
- database
- probability distribution
- data collection
- computational model
- data mining techniques
- data structure
- image data
- knowledge discovery
- probabilistic model
- test data
- network structure
- training data
- associative memory
- neural model
- learned models
- data sources