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

Hybrid NN/HMM acoustic modeling is nowadays an established alternative approach in automatic speech recognition technology. A comparison of feedforward 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.