Speech synthesis by modeling harmonics structure with multiple function.
Toru NakashikaRyuki TachibanaMasafumi NishimuraTetsuya TakiguchiYasuo ArikiPublished in: INTERSPEECH (2010)
Keyphrases
- speech synthesis
- text to speech
- speech recognition
- modeling method
- structural analysis
- piecewise linear
- pattern recognition
- database
- language model
- probabilistic model
- vocal tract
- modeling language
- frequency domain
- multiresolution
- multiscale
- feature extraction
- three dimensional
- website
- computer vision
- neural network
- databases