Lip to Speech Synthesis Based on Speaker Characteristics Feature Fusion.
Rui ZengShengwu XiongPublished in: ITCC (2022)
Keyphrases
- speech synthesis
- feature fusion
- speech recognition
- prosodic features
- vocal tract
- text to speech
- feature extraction
- hidden markov models
- language model
- speaker verification
- multiple features
- high level
- automatic speech recognition
- speech signal
- fusion algorithm
- pattern recognition
- data reduction
- audio visual
- multi sensor
- data fusion
- least squares
- data sets