Comparison of optimization methods for discriminative training criteria
Ralf Schlüter, Wolfgang Macherey, Stephan Kanthak, Hermann Ney, Lutz Welling · 1997
In this work we compare two parameter optimization techniques for discriminative training using the MMI criterion: the extended Baum-Welch (EBW) algorithm and the generalized probabilistic descent (GPD) method.Using Gaussian emission densities we found special expressions for the step sizes in GPD, leading to reestimation formula very similar to those derived for the EBW algorithm.Results were produced for both the TI digitstring and the SieTill corpus for continuously spoken American English and German digitstrings.The results for both techniques do not show signi cant dierences.This experimental results support the strong link between EBW and GPD as expected from the analytic comparison.