GLOBAL OPTIMIZATION OF A NEURAL NETWORK-HIDDEN MARKOV MODEL HYBRID

The subject of this paper is the integration of multilayered and recurrent artificial neural networks (ANN's) with hidden Markov models (HMM's). ANN's are suitable for approximating functions that compute new acoustic parameters, whereas HMM's have been proven successful at modeling the temporal structure of the speech signal. In the approach described here, the ANN outputs constitute the sequence of observation vectors for the HMM. An algorithm is proposed for global optimization of all the parameters. Results on speaker-independent recognition experiments using this integrated ANN-HMM system on the TIMIT continuous speech data base are reported.