Performance trade-offs in search techniques for isolated word speech recognition

The cost effectiveness of various search methods used in experimental and practical discrete utterance speech recognition systems is a very critical factor for the usefulness of such systems. The advantages of some cost effective search techniques, e.g. branch and bound search, branch and bound search with pruning and beam search, have been previoulsy reported. In this paper we analyze the properties that affect the practical usefulness of these algorithms when task characteristics and machine architecture are considered.