Classifying laughter and speech using audio-visual feature prediction.
Stavros PetridisAli AsgharMaja PanticPublished in: ICASSP (2010)
Keyphrases
- visual features
- audio visual
- visual information
- visual data
- content based video retrieval
- audio features
- image classification
- prosodic features
- visual content
- video retrieval
- emotion recognition
- content based retrieval
- multimedia data
- audio stream
- semantic concepts
- video data
- video database
- image search
- text to speech
- multi modal
- low level features
- image annotation
- keywords
- speaker verification
- broadcast news
- image collections
- speech recognition
- low level
- semantic features
- multimedia
- speech synthesis
- computer vision
- web images
- multi party
- soccer video
- image retrieval
- automatic image annotation
- semantic content
- semantic information
- audio signals
- information retrieval
- image content
- object recognition
- global features
- video objects
- multimedia databases
- key frames