Speech recognition system based on visual features and neural network for persons with speech-impairments.
Zhiyan HanXu WangJian WangPublished in: Int. J. Model. Identif. Control. (2009)
Keyphrases
- visual features
- neural network
- visual information
- acoustic features
- content based video retrieval
- image search
- image classification
- audio features
- visual content
- image retrieval
- speech recognition
- image annotation
- semantic features
- audio visual
- low level features
- bag of features
- visual data
- low level
- image collections
- speaker verification
- visual descriptors
- web images
- visual appearance
- global features
- feature extraction
- visual similarity
- semantic gap
- speech signal
- semantic concepts
- keywords
- noisy environments
- automatic speech recognition
- labeled images
- key frames
- bridge the semantic gap