Test of several external posterior weighting functions for multiband Full Combination ASR

摘要

Information about speech reliability can be extracted and hen integrated in a recogniser by various means. The full combination (FC) approach allows the wieghting of the posterior values estiamted locally in the time frequency representation, according a speech reliability measure. Since most of the speech segments are voiced, we use a method exploiting the harmonicity of speech tos derive these weights. We test this method together with the direct integration of the a priori SNR. Then, we run speech recognition iwth differnet kind of weighting functions. The weights are continuous or binary values. Thsi corresponds to a soft or to a hard decision function about the speech reliability, which is derived from an observable harmonicity index. Using a binary decision process, the effect is, for each tiem frame, to collapse the set of combinations of sub-bands into a single combination. On the other hand, we substitue empirical values to these terms, including functions of the a priori SNR, which are continuous or discrete, but not based on a probabilistic estiamtion. We establish the average scores in