Accurate visual speech synthesis based on diviseme unit selection and concatenation.
Dongmei JiangIlse RavyseHichem SahliYanning ZhangPublished in: MMSP (2008)
Keyphrases
- speech synthesis
- speech recognition
- vocal tract
- text to speech
- low level
- visual information
- prosodic features
- high accuracy
- case study
- image sequences
- visual features
- computationally efficient
- selection criteria
- visual perception
- visual cues
- spatial relations
- regular expressions
- highly accurate
- selection algorithm
- database
- hidden markov models
- machine learning