Speech recognition apparatus with speaker adaptation using acoustic category mean value calculus

摘要

Each time a matching unit 22 finishes a matching at a time "i" between feature vectors of input speech which have been converted by an analyzer 1 and feature vectors of reference patterns stored in a reference pattern memory 2, and goes to a matching at a next time "i + 1", a feature vector integrator 24 multiplies the feature vectors of the input speech or the reference patterns by a weight w1 in each of acoustic categories, successively integrates products, stores integrated values in respective frames of the reference patterns in feature vector accumulating buffers 26, and integrates and stores weights w1 in feature vector weight counters 27 corresponding to the respective acoustic categories. When the feature vector integrator 24 finishes integrating and storing processes corresponding to the final matching process, a mean value calculator 28 divides the values stored in the final frames in the feature vector accumulating buffers 26 by the values stored in the feature vector weight counters 27, and outputs the quotients as mean values in the respective acoustic categories of the input speech or the reference patterns. An adaptation unit 55 adapts one or both of the input speech or the reference patterns using the mean values. <IMAGE>