GPD training of dynamic programming-based speech recognizers

概要

論文の詳細を見る
Although many pattern classifiers based on artificial neural networks have been vigorously studied, they are still inadequate from a viewpoint of classifying dynamic(variableand unspecified-duration)speech patterns. To cope with this problems, the generalized probabilistic descent method(GPD)has recently been proposed. GPD not only allows one to train a discriminative system to classify dynamic patterns, but also possesses a remarkable advantage, namely guaranteeing the learning optimality(in the sense of a probabilistic descent search). A practical implementation of this theory, however, remains to be evaluated. In this light, we particularly focus on evaluating GPD in designing a widely-used speech recognizer based on dynamic time warping distancemeasurement. We also show that the design algorithm appraised in this paper can be considered a new version of learning vector quantization results in tasks of classifying syllables and phonemes clearly demonstrate GPD's superiority.
社団法人日本音響学会の論文