Relative Density Nets: A New Way to Combine Backpropagation with HMM's
Andrew D. Brown, Geoffrey E. Hinton · 2001
Logistic units in the rst hidden layer of a feedforward neural network compute the relative probability of a data point under two Gaussians. This leads us to consider substituting other density models. We present an architecture for performing discriminative learning of Hidden Markov Models using a network of many small HMM's. Experiments on speech data show it to be superior to the standard method of discriminatively training HMM's.