Temporal asymmetry in relations of acoustic and visual features of speech.
Gergely FeldhofferTamás BárdiGyörgy TakácsAttila TihanyiPublished in: EUSIPCO (2007)
Keyphrases
- visual features
- acoustic features
- image classification
- visual information
- visual content
- temporal information
- audio features
- image search
- image retrieval
- low level
- visual appearance
- content based video retrieval
- image collections
- low level features
- image annotation
- speech signal
- semantic concepts
- key frames
- semantic features
- web images
- low level visual features
- keywords
- audio visual
- bag of features
- semantic gap
- global features
- speech recognition
- spatio temporal
- speaker verification
- bridge the semantic gap
- speech sounds
- visual patterns
- multi modal
- music information retrieval
- feature space
- object recognition
- feature extraction
- high level
- image processing
- metadata
- computer vision