Speech parameter generation considering LSP ordering property for HMM-based speech synthesis.
Shijun QianHuanliang WangWenjiang PeiPing ZouKai WangPublished in: EUSIPCO (2012)
Keyphrases
- speech synthesis
- speech recognition
- hidden markov models
- text to speech
- vocal tract
- prosodic features
- speech corpus
- parameter values
- total ordering
- speech signal
- partial order
- input parameters
- desirable properties
- variable duration
- generation process
- data sets
- multi modal
- bayesian networks
- feature extraction
- computer vision
- genetic algorithm
- neural network