Speech-to-image media conversion based on VQ and neural network.
Shigeo MorishimaHiroshi HarashimaPublished in: ICASSP (1991)
Keyphrases
- coding scheme
- fractal image coding
- neural network
- single image
- multiscale
- image data
- input image
- image content
- vector quantization
- image features
- image retrieval
- image classification
- image regions
- segmentation method
- image pixels
- image collections
- image segmentation
- image representation
- image compression
- image analysis
- feature points
- speech recognition
- image quality
- edge detection
- low level
- image blocks
- index table
- test images
- high resolution
- audio visual
- locally adaptive
- speaker recognition
- similarity measure