Continuous speech recognition system.

摘要

A continuous speech recognition system for recognizing input speech composed of a plurality of words continuously spoken comprises speech analyzing means for analyzing an input signal at every given frame time point m and outputting an input pattern expressed in a time series of a feature vector consisting of a predetermined number of feature parameters; an input pattern memory to store said input pattern; a reference pattern memory; a distance calculating means to calculate the distance between the feature vector at a time point m (varied from start point to end point M) of said input pattern and the feature vector; an asymptotic calculating means to calculate a similarity measure D(v, n) given by the cumulative sum of said distance at said time points n and a path information F(v, n) indicating a time point of the input pattern; a digit similarity measure and digit path information calculating means to select a minimum similarity measure from among the similarity measures at the end time points of reference patterns of all the words obtained through said asymptotic calculating means; an initializing means to give said digit similarity measure DB(m-1) at a time point (m-1) as an initial value of said similarity measure and to give a time point as an initial value of said path information in said asymptotic calculating means; and a decision means to obtain a recognized result as a final digit from said digit recognition category W(M) at the end point M of said input pattern.