A Two-Pass Pattern-Recognition Approach to Isolated Word Recognition

As illustrated in Fig. 1, the "standard" pattern recognition approach to isolated word recognition is a three-step method consisting of feature measurement, pattern similarity determination, and a decision rule for choosing recognition candidates. This pattern recognition model has been applied to a wide variety of word recognition systems with great success.However, the simple, straightforward approach to word recognition, shown in Fig. 1, runs into difficulties for complex vocabularies, i.e., vocabularies with phonetically similar words. For 739 Fig. 1--Block diagram of standard approach to isolated word recognition.