Multilevel discriminative training for spelled word recognition

Discriminative training is effective in enhancing robustness for recognition tasks characterized by high confusion rates. We apply discriminative training to different components of a spelled word recognizer to improve the recognition accuracy among confusable letters. First we weighted the HMM states to emphasize the letters´ discriminant part. The training achieved a 17% decrease in unit (letter) error rate when the search was performed with an unconstrained grammar. Then we designed a new algorithm that relies on discriminative training to adapt the grammar transition probabilities and the language weight. This method uses acoustic information to provide a tight coupling between the acoustic and language models. Experimental results showed the state weighting followed by the adaptation of a bigram language model reduced by 11% the total unit errors and by 12% the unit errors among the E-Set of the English alphabet