Joint prosodic and segmental unit selection for expressive speech synthesis.
Christophe VeauxPierre LanchantinXavier RodetPublished in: SSW (2010)
Keyphrases
- speech synthesis
- speech recognition
- prosodic features
- text to speech
- hidden markov models
- vocal tract
- text to speech synthesis
- language model
- artificial intelligence
- selection criteria
- non stationary
- speech corpus
- selection algorithm
- databases
- control system
- pattern recognition
- computer vision
- social networks
- machine learning
- real world