Using multimodal speech production data to evaluate articulatory animation for audiovisual speech synthesis.
Ingmar SteinerKorin RichmondSlim OuniPublished in: FAA (2012)
Keyphrases
- speech synthesis
- speech recognition
- data sets
- data sources
- text to speech
- training data
- data structure
- database
- high quality
- raw data
- synthetic data
- vocal tract
- data collection
- data analysis
- data points
- audio visual
- speech signal
- end users
- neural network
- data processing
- multi modal
- high dimensional data
- data mining techniques
- image data
- visual information