A signature tree is a binary decision tree used to classify unknown patterns. An attempt was made to develop a computer program for manipulating signature trees as a general research tool for exploring machine learning and pattern recognition. The program was applied to the problem of speech recognition to test its effectiveness for a specific case. The signature tree heuristic requires a data base of known patterns stored in an array called the lexicon. When the data base of given utterances is insufficient to establish trends with confidence, a large number of "feature extractors" are employed and recognition of an unknown pattern is made by comparing its feature values with those of the lexicon. When the data base is replete, a signature tree can be constructed and recognition can be achieved by the evaluation of a select few features. Learning results from selecting an optimal minimal set of features to achieve recognition. Moderate success was attained in the application of the program to a speech recognition problem. (Author/JY)