期刊名称：International Journal of Managing Information Technology
印刷版ISSN：0975-5926
电子版ISSN：0975-5586
出版年度：2010
卷号：2
期号：1
出版社：Academy & Industry Research Collaboration Center (AIRCC)
摘要：Speech is the predominant mode of human communication for every day interaction. Speech will also be the preferred mode for human-machine interaction. The study of human-machine communication comes in the area of intelligent query processing. This paper discusses a novel technique for recognition of the isolated question words from speech queries, which leads to the first step to identify the question type. Here we have created and analyzed a database of 250 question words from Malayalam (one of the south Indian language) speech queries. We have used Daubechies wavelets for the speech feature extraction purpose. We have used the Multi Layer Perceptron (MLP) Architecture and Piecewise Network Classifier (PLN) is used for classification and recognition. A recognition accuracy of 72% could be achieved from this experiment for Multi Layer Perceptron classifier and 60% for the Piecewise Network Classifier
