Hi, when I reproduce the causality in SGMSE (actual in SGMSE-BBED) as the paper 'SPEECH SIGNAL IMPROVEMENT USING CAUSAL GENERATIVE DIFFUSION MODELS' in ICASSP2023. I make the following changement for score model ncsnpp+ as in paper :
add causal pad for 3*3conv2d.
block the attention module
block the Groupnorm
replace the layerspp.ResnetBlockBigGANpp's downsample_2d, upsample_2d with causal conv2d and TransposedConv2D,block the groupnorm in module
replace the layerspp.Downsample Upsample as above in 4.
But it still not work, could you give me some advice on it, Thanks!
Hi, when I reproduce the causality in SGMSE (actual in SGMSE-BBED) as the paper 'SPEECH SIGNAL IMPROVEMENT USING CAUSAL GENERATIVE DIFFUSION MODELS' in ICASSP2023. I make the following changement for score model ncsnpp+ as in paper :
But it still not work, could you give me some advice on it, Thanks!