The sequential structure and variable length of speech data suggest the use of structural techniques such as Hidden Markov Models or Grammatical Inference systems. In contrast, decision theoretic-based on "geometric" and classical (non-recurrent) connectionist methods deal with objects represented in a metric and/or vector space. This means that some technique has to be used to transform variable-length strings of parameters into d-dimensional vectors. Several such methods exist and some of them have been tested in this work in a difficult isolated word recognition task. The results of experiments with k-Nearest Neighbor, Multilayer Perceptron and Decision Surface Mapping are compared with others already reported using Hidden Markov Models, Error Correcting Grammatical Inference and Morphic Generator Grammatical Inference systems.

Keywords: Pattern Recognition, Isolated Word Recognition.