Hidden Markov model/neural network training techniques for connected alphadigit speech recognition

A neural network formulation for an HMM (hidden Markov model) is presented, and training using maximum likelihood, maximum mutual information, minimum mean-squared-error (MMSE), and unconstrained MMSE is described. Recognition results are presented for the variously trained models evaluated on a speaker-independent, connected alphadigit speech recognition task. It is concluded that viewing neural networks as HMMs provides a framework for building temporally dependent neural networks, while viewing HMMs as neural networks broadens the class of natural training methods. Despite several drawbacks, performance results indicate that models trained with error-correcting criteria on sufficient amounts of data may do better at discriminating similar sounds