Speech Dereverberation by Combining Mint-Based Blind Deconvolution and Modified Spectral Subtraction.
Ken'ichi FuruyaSumitaka SakauchiAkitoshi KataokaPublished in: ICASSP (1) (2006)
Keyphrases
- blind deconvolution
- speech signal
- spectral subtraction
- speech recognition
- total variation
- automatic speech recognition
- image deblurring
- speech enhancement
- multi frame
- blurred images
- noise reduction
- point spread function
- noisy environments
- non stationary
- map estimation
- linear prediction
- image restoration
- denoising
- bayesian framework
- synthetic and real images
- additive noise
- image denoising
- vocal tract
- language model