Automatic feature selection for acoustic-visual concatenative speech synthesis: towards a perceptual objective measure.
Utpala MustiVincent ColotteSlim OuniCaroline LavecchiaBrigitte Wrobel-DautcourtMarie-Odile BergerPublished in: AVSP (2013)
Keyphrases
- speech synthesis
- prosodic features
- speech recognition
- visual perception
- text to speech
- low level
- visual information
- human visual
- vocal tract
- visual processing
- cross modal
- human vision
- probabilistic model
- speech corpus
- empirically derived
- image quality assessment
- similarity measure
- high level
- human perceptual
- subjective evaluation
- human visual system
- underwater vehicles
- visual features
- distance measure
- image quality measures
- computer vision
- quality metrics
- image processing
- perceptual information
- speaker verification
- quality assessment
- human perception
- perceptual organization
- visual data
- visual search