Bayesian inference is a sophisticated technique that has been recently applied to gravitational radiation signals from core collapse supernovae in order to increase the chances of a successful detection. In this talk I present results obtained in my master thesis where I explored the possibilities and limitations of this technique. For my study I make use of gravitational waveform libraries obtained through numerical simulations of stellar core collapse. These catalogs contain waveforms produced by three different explosion mechanisms, namely rotational, neutrino, and acoustic. An orthogonal set of eigenvectors is created using principal components analysis and Bayesian inference techniques are used to reconstruct the most probable waveform and to obtain the posterior distribution of system parameters. The study of these distributions provides an estimation of the physical parameters associated with the supernova explosion.