A hybrid statistical/RNN approach to prosody synthesis for taiwanese TTS.
Sin-Horng ChenChen-Chung HoPublished in: INTERSPEECH (2000)
Keyphrases
- text to speech
- recurrent neural networks
- speech synthesis
- prosodic features
- statistical analysis
- language learning
- statistical methods
- nearest neighbor
- hybrid approaches
- program synthesis
- learning strategies
- statistical models
- data driven
- university students
- neural network
- video sequences
- training set
- word processing
- cooperative learning
- confidence intervals
- learning tools
- information theoretic