Support vector machines versus fast scoring in the low-dimensional total variability space for speaker verification.
Najim DehakRéda DehakPatrick KennyNiko BrümmerPierre OuelletPierre DumouchelPublished in: INTERSPEECH (2009)
Keyphrases
- low dimensional
- speaker verification
- support vector
- high dimensional
- dimensionality reduction
- input space
- data points
- noisy environments
- principal component analysis
- feature space
- high dimensional data
- feature selection
- prosodic features
- audio visual
- object detection
- emotion recognition
- multiscale
- speaker recognition
- multimedia