A training algorithm for statistical sequence recognition with applications to transition-based speech recognition

In this letter, we introduce a discriminant training algorithm for statistical sequence recognition that uses a transition-based stochastic finite state automaton with posterior transition probabilities conditioned on the current input observation and the previous state. This provides a framework for frame-synchronous speech recognition in which posterior probabilities are estimated as the basis for recognition, rather than the state-dependent probability densities that are conventionally used. Preliminary speech recognition experiments support the theory by showing an increase in the estimates of posterior probabilities of the correct sentences and a statistically significant decrease in error rates for independent test sets.