Audiovisual speech source separation: a regularization method based on visual voice activity detection.
Bertrand RivetLaurent GirinChristine ServièreDinh-Tuan PhamChristian JuttenPublished in: AVSP (2007)
Keyphrases
- voice activity detection
- regularization method
- source separation
- visual information
- audio visual
- noisy environments
- audio features
- speech recognition
- blind source separation
- image restoration
- visual features
- regularization parameter
- independent component analysis
- visual data
- speech signal
- denoising
- low level
- information retrieval
- gaussian mixture model
- multiresolution
- single channel
- feature space
- pattern recognition