Mercurial > hg > smallbox
diff Problems/generateAudioDeclippingProblem.m @ 164:4205744092e6 release_1.9
Merge from branch "ivand_dev"
author | Ivan Damnjanovic lnx <ivan.damnjanovic@eecs.qmul.ac.uk> |
---|---|
date | Wed, 07 Sep 2011 14:17:30 +0100 |
parents | f42aa8bcb82f |
children | 9c418bea7f6a |
line wrap: on
line diff
--- a/Problems/generateAudioDeclippingProblem.m Tue Jul 26 16:02:59 2011 +0100 +++ b/Problems/generateAudioDeclippingProblem.m Wed Sep 07 14:17:30 2011 +0100 @@ -5,6 +5,35 @@ % Audio declipping is a problem proposed in Audio Inpaining Toolbox and % in [2]. % +% The function takes as an optional input +% soundfile - name of the file +% clippingLevel - (default 0.6) +% windowSize - 1D frame size (eg 512) +% overlap - ammount of overlaping frames between 0 and 1 +% wa,ws,wd - analisys, synthesis and dictionary window functions +% +% Dict_fun - function to be used to generate dictionary +% redundancyFactor - overcompletness of dictionary (default 2) +% +% The function outputs the structure with following fields: +% original - original signal +% clipped - clipped signal +% clipMask - mask indicating clipped samples +% clippingLevel - (default 0.6) +% Upper_Limit - maximum value of original data +% fs - sample rate of the original signal in Hertz +% nbits - the number of bits per sample +% sigma - added noise level +% B - dictionary to be used for sparse representation +% M - measurement matrix (non-clipped data in b) +% b - matrix of clipped frames +% m - size od dictionary atom +% n - number of frames to be represented +% p - number of atoms in dictionary +% windowSize - 1D frame size (eg 512) +% overlap - ammount of overlaping frames between 0 and 1 +% wa,ws, wd - analisys, synthesis and dictionary window functions +% % [1] I. Damnjanovic, M. E. P. Davies, and M. P. Plumbley "SMALLbox - an % evaluation framework for sparse representations and dictionary % learning algorithms," V. Vigneron et al. (Eds.): LVA/ICA 2010, @@ -103,7 +132,7 @@ data.fs = x.fs; data.nbits = x.nbits; - +data.Upper_Limit = max(solutionData.xClean); [data.m, data.n] = size(x_clip); data.p = windowSize*redundancyFactor; %number of dictionary elements