Continuous speech recognition without segmentation: Two ways of using diphones as basic speech units.
Carlo ScagliolaPublished in: Speech Commun. (1983)
Keyphrases
- continuous speech recognition
- level set
- segmentation algorithm
- segmentation method
- image segmentation
- medical images
- texture segmentation
- multiscale
- edge detection
- neural network
- energy function
- segmentation errors
- region growing
- speech recognition
- fully automatic
- graph cuts
- background subtraction
- multiresolution
- image sequences
- image processing
- computer vision