device for pattern recognition with a neural network model for kontextabhaengige columns

摘要

A pattern (for example speech) recognition device comprising an artificial neural network set-up having K X M output units and provided for calculating probabilities of observing a feature vector (xt) (12) on a class (qk) (1 /= k /= K) (11) conditioned on predetermined contextual models (cm) (1 /= m /= M) (17), each of said classes being represented by at least one model belonging to a finite set of models (M) governed by statistical laws. Said neural network set-up is splitted into a first neural network having K output units and being provided for calculating a posteriori probabilities of said class (qk) given said observed vector (xt), and at least one further neural network having M output units and provided for calculating a posteriori probabilities of said contextual models, conditioned on said class.