HMM speech synthesis based on MDCT representation.
Giorgio BiagettiPaolo CrippaLaura FalaschettiClaudio TurchettiPublished in: Int. J. Speech Technol. (2018)
Keyphrases
- speech synthesis
- speech recognition
- hidden markov models
- vocal tract
- text to speech
- database
- speech signal
- visual speech recognition
- automatic speech recognition
- image representation
- mobile robot
- gesture recognition
- feature representation
- representation scheme
- maximum likelihood
- forward backward
- bayesian networks
- decision trees