Tuning intonation with pitch accent decomposition for HMM-based expressive speech synthesis.
Jinfu NiYoshinori ShigaChiori HoriPublished in: APSIPA (2014)
Keyphrases
- speech synthesis
- speech recognition
- prosodic features
- hidden markov models
- text to speech
- automatic speech recognition
- vocal tract
- speech signal
- language model
- pattern recognition
- decomposition method
- acoustic features
- noisy environments
- decomposition methods
- image processing
- database systems
- image decomposition
- multiscale
- relational databases
- speaker verification
- database
- parameter settings
- feature selection
- rule selection
- data mining