Neural networks for nonlinear discriminant analysis in continuous speech recognition
Wolfgang Reichl, Steffen Harengel, Franz Wolfertstetter, Günther Ruske · OpenGrey (Institut de l'Information Scientifique et Technique) · 1996
In this paper neural networks for Nonlinear Discriminant Analysis in continuous speech recognition are presented. Multilayer Perceptrons are used to estimate a-posteriori probabilities for Hidden-Markov Model states, which are the optimal discriminant features for the separation of the HMM states. The a-posteriori probabilities are transformed by a principal component analysis to calculate the new features for semicontinuous HMMs, which are trained by known Maximum-Likelihood training. The nonlinear discriminant transformation is used in speaker-independent phoneme recognition experiments and compared to the standard Linear Discriminant Analysis technique. (orig.)