Apparatus and method of grouping utterances of a phoneme into context-de-pendent categories based on sound-similarity for automatic speech recognition.

摘要

A method and apparatus of automatically grouping observed events into similar categories and correlating groups of observed events with different contexts, and an automatic speech recognition method and apparatus which utilizes the context-dependent groupings. Symbol feature values and contextual feature values of each event in a training set of events are measured. At least two pairs of complementary subsets of observed events are selected. In each pair of complementary subsets of observed events, one subset has contextual features with values in a set Cn, and the other set has contextual features with values in a set <MATH> were the sets in Cn and <MATH> are complementary sets of contextual feature values. For each subset of observed events, the similarity values of the symbol features of the observed events in the subsets are calculated. For each pair of complementary sets of observed events, a "goodness of fit" is the sum of the symbol feature value similarity of the subsets. The sets of contextual feature values associated with the subsets of observed events having the best "goodness of fit" are identified and form context-dependent bases for grouping the observed events into two output sets. <IMAGE>