A waveform representation framework for high-quality statistical parametric speech synthesis.
Bo FanSiu Wa LeeXiaohai TianLei XieMinghui DongPublished in: APSIPA (2015)
Keyphrases
- high quality
- speech synthesis
- representation scheme
- computer vision
- main contribution
- neural network
- representation language
- speech recognition
- level set
- data representations
- higher quality
- low quality
- statistical models
- real time
- ground truth
- probabilistic model
- hidden markov models
- face recognition
- machine learning
- data sets