Speech Recognition Using context Conditional word Posterior Probabilities

摘要

In this paper two new scoring schemes for large vocabulary continuous speech recognition are compared. Instead of using the joint probability of a word sequence and a sequence of acoustic observations, we determien the best path through a word graph using posterior word probabilities with or without word context. The exact calulation of the posterior probability for a word sequence implies a sum over all possible word boundaries, which is approximated by a maximum operation in the standard scoring approach. The new scoring scheme using word posterior probabilities could be expected to lead to improved recognition performance, because it involves partial summation over word boundaries. We present experimetnal results on five differnet corpora, the Dutch Arise corpus, the German Verbmobil '98 corpus, the English North American Business '94 20k and 64k development corpora, and the English Broadcast News '96 corpus. It is shown that the Viterbi approxiamtion within words has no efect on standard and word posterior based recognition. Using word posteriro probabilities with an without word context, the relative reduction in word error rate is comparable and ranges between 1.5