Emotional Audio-Visual Speech Synthesis Based on PAD.
Jia JiaShen ZhangFanbo MengYongxin WangLianhong CaiPublished in: IEEE Trans. Speech Audio Process. (2011)
Keyphrases
- audio visual
- speech synthesis
- emotion recognition
- speech recognition
- multi modal
- text to speech
- affective states
- visual information
- vocal tract
- multimedia
- visual data
- speaker verification
- data sets
- multi stream
- temporal context
- emotional state
- pattern recognition
- person authentication
- audio visual speech recognition
- space time
- hidden markov models
- noisy environments
- speech signal
- domain knowledge
- spatio temporal
- image sequences