Prosody for the eyes: quantifying visual prosody using guided principal component analysis.
Erin CvejicJeesun KimChris DavisGuillaume GibertPublished in: INTERSPEECH (2010)
Keyphrases
- principal component analysis
- text to speech
- speech synthesis
- prosodic features
- synthesized speech
- independent component analysis
- visual features
- face recognition
- multi stream
- audio visual
- principal components
- covariance matrix
- neural network
- visual information
- dimension reduction
- speech recognition
- visual cues
- low dimensional
- dimensionality reduction
- low level
- feature extraction
- feature selection