Speech recognition using demi-syllable neural prediction model

Abstract

The Neural Prediction Model is the speech recognition model based on pattern prediction by multilayer perceptrons. Its effectiveness was confirmed by the speaker-independent digit recognition experiments. This paper presents an improvement in the model and its application to large vocabulary speech recognition, based on subword units. The improvement involves an introduction of backward prediction, which further improves the prediction accuracy of the original model with only forward prediction. In application of the model to speaker-dependent large vocabulary speech recognition, the demi-syllable unit is used as a subword recognition unit. Experimental results indicated a 95.2% recognition accuracy for a 5000 word test set and the effectiveness was confirmed for the proposed model improvement and the demi-syllable subword units.