Setup for acoustic-visual speech synthesis by concatenating bimodal units.
Asterios ToutiosUtpala MustiSlim OuniVincent ColotteBrigitte Wrobel-DautcourtMarie-Odile BergerPublished in: INTERSPEECH (2010)
Keyphrases
- speech synthesis
- prosodic features
- speech recognition
- text to speech
- vocal tract
- visual features
- speech recognition systems
- visual information
- visual perception
- low level
- underwater acoustic
- source localization
- visual representation
- processing units
- face recognition
- visual cues
- image classification
- hidden markov models