A Method for Speech Dereverberation Based on an Image Deblurring Algorithm Using the Prior of Speech Magnitude Gradient Distribution in the Time-Frequency Domain.
Wonyong JoJi-Won ChoChangsoo JeHyung-Min ParkPublished in: HAI (2015)
Keyphrases
- computational complexity
- detection algorithm
- synthetic and real images
- segmentation algorithm
- prior information
- energy function
- probabilistic model
- estimation algorithm
- segmentation method
- image deblurring
- closed form
- blind deconvolution
- similarity measure
- speech recognition
- model selection
- bayesian framework
- digital image processing
- em algorithm
- feature extraction