Picture my voice: Audio to visual speech synthesis using artificial neural networks.
Dominic W. MassaroJonas BeskowMichael M. CohenChristopher L. FryTony RodriguezPublished in: AVSP (1999)
Keyphrases
- using artificial neural networks
- speech synthesis
- text to speech
- prosodic features
- speech recognition
- visual information
- speaker verification
- artificial neural networks
- vocal tract
- visual data
- cross modal
- multimodal interaction
- visual features
- low level
- finite element analysis
- visual speech
- neural network model
- english text
- audio visual
- friction coefficient
- visually impaired users
- word processing
- multimedia
- multi modal
- speech corpus