Emotional statistical parametric speech synthesis using LSTM-RNNs.
Shumin AnZhenhua LingLirong DaiPublished in: APSIPA (2017)
Keyphrases
- speech synthesis
- recurrent neural networks
- long short term memory
- speech recognition
- text to speech
- recurrent networks
- feedforward neural networks
- vocal tract
- data driven
- statistical analysis
- feed forward
- prosodic features
- hidden markov models
- neural network
- echo state networks
- hypothesis testing
- input output
- statistical inference
- confidence intervals
- statistical tests
- probabilistic model
- neuro fuzzy
- statistical significance
- database
- statistical methods
- emotional intelligence
- artificial neural networks
- feature extraction
- learning algorithm
- information retrieval
- information theoretic
- language model
- real time