Recurrent input transformations for Hidden Markov models

This paper presents a new architecture which integrates recurrent input transformations (RIT) and continuous density HMMs. The basic HMM structure is extended to accommodate recurrent neural networks which transform the input observations before they enter the Gaussian output distributions associated with the states of the HMM. During training the parameters of both HMM and RIT are simultaneously optimized according to the Maximum Mutual Information (MMI) criterion. Results are presented for the E-set recognition task which demonstrate the ability of recurrent input transformations to exploit longer term correlations in the speech signal and to give improved discrimination.