Speech/Non-Speech Detection in Meetings from Automatically Extracted low Resolution Visual Features.
Hayley HungSileye O. BaPublished in: ICASSP (2010)
Keyphrases
- visual features
- low resolution
- automatically extracted
- high resolution
- super resolution
- audio visual
- visual information
- speech recognition
- image classification
- visually similar
- low resolution images
- visual content
- visual data
- image retrieval
- high resolution images
- image super resolution
- image search
- low level
- higher resolution
- keywords
- high quality
- low level features
- speech signal
- face images
- multimedia
- super resolution reconstruction
- semantic concepts
- automatic speech recognition
- face recognition
- image patches
- depth images
- depth map
- markov random field
- multiresolution
- high dimensional
- high level