Triphone based unit selection for concatenative visual speech synthesis.
Fu Jie HuangEric CosattoHans Peter GrafPublished in: ICASSP (2002)
Keyphrases
- speech synthesis
- speech corpus
- speech recognition
- text to speech
- vocal tract
- prosodic features
- visual information
- selection criteria
- data sets
- selection algorithm
- hidden markov models
- genetic algorithm
- data mining
- spatial relations
- visual data
- visual perception
- pattern recognition
- information systems
- computer vision
- database