Comparing NN paradigms in hybrid NN/HMM speech recognition using tied posteriors

Hybrid NN/HAM acoustic modeling is nowadays an established alternative approach in automatic speech recognition technology. A comparison of feed-forward and recurrent neural network topologies integrated in the tied-posteriors framework is presented. We give some insights in the training process of the networks estimating class posterior probabilities and show how the net's quality can be determined by introducing a new measurement prior to evaluating the complete ASR system. Finally we demonstrate the flexibility of the tied-posteriors framework by showing results for different context independent and context dependent acoustic models all based on the same system structure.