Word Set Probability Boosting for Improved Spontaneous Dialogue Recognition: The AB/TAB Algorithms
Ramesh R. Sarukkai, Dana H. Ballard · 1995
Based on the observation that the unpredictable nature of conversational speech makes it almost impossible to reliably model sequential word constraints, the notion of word set error criteria is proposed for improved recognition of spontaneous dialogues. The single pass Adaptive Boosting (AB) algorithm enables the language model weights to be tuned using the word set error criteria. In the two pass version of the algorithm, the basic idea is to predict a set of words based on some a priori information, and perform a re-scoring pass wherein the probabilities of the words in the predicted word set are amplified or boosted in some manner. An adaptive gradient descent procedure for tuning the word boosting factor has been formulated which enables the boost factors to be incrementally adjusted to maximize accuracy of the speech recognition system outputs on held-out training data using the word set error criteria . Two novel models which predict the required word sets have been presented: u...