Title :
Robust noise modelling with application to audio restoration
Author :
Godsill, Simon J. ; Rayner, Peter J W
Author_Institution :
Signal Process. & Commun. Lab., Cambridge Univ., UK
Abstract :
New methods are presented for robust modelling of noise sources drawn from heavy-tailed or impulsive distributions, such as are commonly encountered in communications systems and corrupted audio signals. The methods are formulated for linear signal models within a Bayesian framework (although likelihood-based results are easily obtained as a subset of the Bayesian methods). Solutions are generated using powerful iterative techniques. Investigations are carried out for an audio interpolation framework in which certain samples are corrupted with additive impulsive noise
Keywords :
Bayes methods; acoustic noise; acoustic signal processing; audio signals; interpolation; iterative methods; signal restoration; Bayesian framework; additive impulsive noise; audio restoration; heavy-tailed distributions; impulsive distributions; iterative techniques; likelihood-based results; linear signal models; noise sources; robust noise modelling; Additive noise; Bayesian methods; Covariance matrix; Gaussian noise; Interpolation; Microscopy; Noise level; Noise robustness; Signal processing; Signal restoration;
Conference_Titel :
Applications of Signal Processing to Audio and Acoustics, 1995., IEEE ASSP Workshop on
Conference_Location :
New Paltz, NY
Print_ISBN :
0-7803-3064-1
DOI :
10.1109/ASPAA.1995.482977
