In this paper we demonstrate the use of Bayesian analysis methods for
the removal or suppression of solvent peaks from NMR spectra. Typicall
y solvent peaks are the dominant feature in the NMR spectrum and often
mask or seriously overlap smaller resonance from which important info
rmation of the molecule under study may be obtained. Although applied
to NMR spectra, the method is general and may be applied to large peak
suppression in most spectroscopic techniques.